Skip to content

Realtime

ModelsExpand Collapse
type AudioTranscription struct{…}
Language stringoptional

The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

Model AudioTranscriptionModeloptional

The model to use for transcription. Current options are whisper-1, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-transcribe, and gpt-4o-transcribe-diarize. Use gpt-4o-transcribe-diarize when you need diarization with speaker labels.

Accepts one of the following:
string
type AudioTranscriptionModel string

The model to use for transcription. Current options are whisper-1, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-transcribe, and gpt-4o-transcribe-diarize. Use gpt-4o-transcribe-diarize when you need diarization with speaker labels.

Accepts one of the following:
const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"
const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"
const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"
const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"
const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"
Prompt stringoptional

An optional text to guide the model's style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models (excluding gpt-4o-transcribe-diarize), the prompt is a free text string, for example "expect words related to technology".

type ConversationCreatedEvent struct{…}

Returned when a conversation is created. Emitted right after session creation.

Conversation ConversationCreatedEventConversation

The conversation resource.

ID stringoptional

The unique ID of the conversation.

Object stringoptional

The object type, must be realtime.conversation.

EventID string

The unique ID of the server event.

Type ConversationCreated

The event type, must be conversation.created.

type ConversationItemUnion interface{…}

A single item within a Realtime conversation.

Accepts one of the following:
type RealtimeConversationItemSystemMessage struct{…}

A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages.

Content []RealtimeConversationItemSystemMessageContent

The content of the message.

Text stringoptional

The text content.

Type stringoptional

The content type. Always input_text for system messages.

Role System

The role of the message sender. Always system.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemSystemMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemSystemMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"
const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"
const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"
type RealtimeConversationItemUserMessage struct{…}

A user message item in a Realtime conversation.

Content []RealtimeConversationItemUserMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes (for input_audio), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Detail stringoptional

The detail level of the image (for input_image). auto will default to high.

Accepts one of the following:
const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"
const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"
const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"
ImageURL stringoptional

Base64-encoded image bytes (for input_image) as a data URI. For example data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA.... Supported formats are PNG and JPEG.

Text stringoptional

The text content (for input_text).

Transcript stringoptional

Transcript of the audio (for input_audio). This is not sent to the model, but will be attached to the message item for reference.

Type stringoptional

The content type (input_text, input_audio, or input_image).

Accepts one of the following:
const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"
const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"
const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"
Role User

The role of the message sender. Always user.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemUserMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemUserMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"
const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"
const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"
type RealtimeConversationItemAssistantMessage struct{…}

An assistant message item in a Realtime conversation.

Content []RealtimeConversationItemAssistantMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Text stringoptional

The text content.

Transcript stringoptional

The transcript of the audio content, this will always be present if the output type is audio.

Type stringoptional

The content type, output_text or output_audio depending on the session output_modalities configuration.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"
const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"
Role Assistant

The role of the message sender. Always assistant.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemAssistantMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemAssistantMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"
const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"
const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"
type RealtimeConversationItemFunctionCall struct{…}

A function call item in a Realtime conversation.

Arguments string

The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example {"arg1": "value1", "arg2": 42}.

Name string

The name of the function being called.

Type FunctionCall

The type of the item. Always function_call.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

CallID stringoptional

The ID of the function call.

Object RealtimeConversationItemFunctionCallObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"
const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"
const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"
type RealtimeConversationItemFunctionCallOutput struct{…}

A function call output item in a Realtime conversation.

CallID string

The ID of the function call this output is for.

Output string

The output of the function call, this is free text and can contain any information or simply be empty.

Type FunctionCallOutput

The type of the item. Always function_call_output.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemFunctionCallOutputObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallOutputStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"
const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"
const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"
type RealtimeMcpApprovalResponse struct{…}

A Realtime item responding to an MCP approval request.

ID string

The unique ID of the approval response.

ApprovalRequestID string

The ID of the approval request being answered.

Approve bool

Whether the request was approved.

Type McpApprovalResponse

The type of the item. Always mcp_approval_response.

Reason stringoptional

Optional reason for the decision.

type RealtimeMcpListTools struct{…}

A Realtime item listing tools available on an MCP server.

ServerLabel string

The label of the MCP server.

Tools []RealtimeMcpListToolsTool

The tools available on the server.

InputSchema any

The JSON schema describing the tool's input.

Name string

The name of the tool.

Annotations anyoptional

Additional annotations about the tool.

Description stringoptional

The description of the tool.

Type McpListTools

The type of the item. Always mcp_list_tools.

ID stringoptional

The unique ID of the list.

type RealtimeMcpToolCall struct{…}

A Realtime item representing an invocation of a tool on an MCP server.

ID string

The unique ID of the tool call.

Arguments string

A JSON string of the arguments passed to the tool.

Name string

The name of the tool that was run.

ServerLabel string

The label of the MCP server running the tool.

Type McpCall

The type of the item. Always mcp_call.

ApprovalRequestID stringoptional

The ID of an associated approval request, if any.

Error RealtimeMcpToolCallErrorUnionoptional

The error from the tool call, if any.

Accepts one of the following:
type RealtimeMcpProtocolError struct{…}
Code int64
Message string
Type ProtocolError
type RealtimeMcpToolExecutionError struct{…}
Message string
Type ToolExecutionError
type RealtimeMcphttpError struct{…}
Code int64
Message string
Type HTTPError
Output stringoptional

The output from the tool call.

type RealtimeMcpApprovalRequest struct{…}

A Realtime item requesting human approval of a tool invocation.

ID string

The unique ID of the approval request.

Arguments string

A JSON string of arguments for the tool.

Name string

The name of the tool to run.

ServerLabel string

The label of the MCP server making the request.

Type McpApprovalRequest

The type of the item. Always mcp_approval_request.

type ConversationItemAdded struct{…}

Sent by the server when an Item is added to the default Conversation. This can happen in several cases:

  • When the client sends a conversation.item.create event.
  • When the input audio buffer is committed. In this case the item will be a user message containing the audio from the buffer.
  • When the model is generating a Response. In this case the conversation.item.added event will be sent when the model starts generating a specific Item, and thus it will not yet have any content (and status will be in_progress).

The event will include the full content of the Item (except when model is generating a Response) except for audio data, which can be retrieved separately with a conversation.item.retrieve event if necessary.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

Type ConversationItemAdded

The event type, must be conversation.item.added.

PreviousItemID stringoptional

The ID of the item that precedes this one, if any. This is used to maintain ordering when items are inserted.

type ConversationItemCreateEvent struct{…}

Add a new Item to the Conversation's context, including messages, function calls, and function call responses. This event can be used both to populate a "history" of the conversation and to add new items mid-stream, but has the current limitation that it cannot populate assistant audio messages.

If successful, the server will respond with a conversation.item.created event, otherwise an error event will be sent.

A single item within a Realtime conversation.

Type ConversationItemCreate

The event type, must be conversation.item.create.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
PreviousItemID stringoptional

The ID of the preceding item after which the new item will be inserted. If not set, the new item will be appended to the end of the conversation.

If set to root, the new item will be added to the beginning of the conversation.

If set to an existing ID, it allows an item to be inserted mid-conversation. If the ID cannot be found, an error will be returned and the item will not be added.

type ConversationItemCreatedEvent struct{…}

Returned when a conversation item is created. There are several scenarios that produce this event:

  • The server is generating a Response, which if successful will produce either one or two Items, which will be of type message (role assistant) or type function_call.
  • The input audio buffer has been committed, either by the client or the server (in server_vad mode). The server will take the content of the input audio buffer and add it to a new user message Item.
  • The client has sent a conversation.item.create event to add a new Item to the Conversation.
EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

Type ConversationItemCreated

The event type, must be conversation.item.created.

PreviousItemID stringoptional

The ID of the preceding item in the Conversation context, allows the client to understand the order of the conversation. Can be null if the item has no predecessor.

type ConversationItemDeleteEvent struct{…}

Send this event when you want to remove any item from the conversation history. The server will respond with a conversation.item.deleted event, unless the item does not exist in the conversation history, in which case the server will respond with an error.

ItemID string

The ID of the item to delete.

Type ConversationItemDelete

The event type, must be conversation.item.delete.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type ConversationItemDeletedEvent struct{…}

Returned when an item in the conversation is deleted by the client with a conversation.item.delete event. This event is used to synchronize the server's understanding of the conversation history with the client's view.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item that was deleted.

Type ConversationItemDeleted

The event type, must be conversation.item.deleted.

type ConversationItemDone struct{…}

Returned when a conversation item is finalized.

The event will include the full content of the Item except for audio data, which can be retrieved separately with a conversation.item.retrieve event if needed.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

Type ConversationItemDone

The event type, must be conversation.item.done.

PreviousItemID stringoptional

The ID of the item that precedes this one, if any. This is used to maintain ordering when items are inserted.

type ConversationItemInputAudioTranscriptionCompletedEvent struct{…}

This event is the output of audio transcription for user audio written to the user audio buffer. Transcription begins when the input audio buffer is committed by the client or server (when VAD is enabled). Transcription runs asynchronously with Response creation, so this event may come before or after the Response events.

Realtime API models accept audio natively, and thus input transcription is a separate process run on a separate ASR (Automatic Speech Recognition) model. The transcript may diverge somewhat from the model's interpretation, and should be treated as a rough guide.

ContentIndex int64

The index of the content part containing the audio.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item containing the audio that is being transcribed.

Transcript string

The transcribed text.

Type ConversationItemInputAudioTranscriptionCompleted

The event type, must be conversation.item.input_audio_transcription.completed.

Usage ConversationItemInputAudioTranscriptionCompletedEventUsageUnion

Usage statistics for the transcription, this is billed according to the ASR model's pricing rather than the realtime model's pricing.

Accepts one of the following:
ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokens
InputTokens int64

Number of input tokens billed for this request.

OutputTokens int64

Number of output tokens generated.

TotalTokens int64

Total number of tokens used (input + output).

Type Tokens

The type of the usage object. Always tokens for this variant.

InputTokenDetails ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokensInputTokenDetailsoptional

Details about the input tokens billed for this request.

AudioTokens int64optional

Number of audio tokens billed for this request.

TextTokens int64optional

Number of text tokens billed for this request.

ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageDuration
Seconds float64

Duration of the input audio in seconds.

Type Duration

The type of the usage object. Always duration for this variant.

Logprobs []LogProbPropertiesoptional

The log probabilities of the transcription.

Token string

The token that was used to generate the log probability.

Bytes []int64

The bytes that were used to generate the log probability.

Logprob float64

The log probability of the token.

type ConversationItemInputAudioTranscriptionDeltaEvent struct{…}

Returned when the text value of an input audio transcription content part is updated with incremental transcription results.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item containing the audio that is being transcribed.

Type ConversationItemInputAudioTranscriptionDelta

The event type, must be conversation.item.input_audio_transcription.delta.

ContentIndex int64optional

The index of the content part in the item's content array.

Delta stringoptional

The text delta.

Logprobs []LogProbPropertiesoptional

The log probabilities of the transcription. These can be enabled by configurating the session with "include": ["item.input_audio_transcription.logprobs"]. Each entry in the array corresponds a log probability of which token would be selected for this chunk of transcription. This can help to identify if it was possible there were multiple valid options for a given chunk of transcription.

Token string

The token that was used to generate the log probability.

Bytes []int64

The bytes that were used to generate the log probability.

Logprob float64

The log probability of the token.

type ConversationItemInputAudioTranscriptionFailedEvent struct{…}

Returned when input audio transcription is configured, and a transcription request for a user message failed. These events are separate from other error events so that the client can identify the related Item.

ContentIndex int64

The index of the content part containing the audio.

Error ConversationItemInputAudioTranscriptionFailedEventError

Details of the transcription error.

Code stringoptional

Error code, if any.

Message stringoptional

A human-readable error message.

Param stringoptional

Parameter related to the error, if any.

Type stringoptional

The type of error.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item.

Type ConversationItemInputAudioTranscriptionFailed

The event type, must be conversation.item.input_audio_transcription.failed.

type ConversationItemInputAudioTranscriptionSegment struct{…}

Returned when an input audio transcription segment is identified for an item.

ID string

The segment identifier.

ContentIndex int64

The index of the input audio content part within the item.

End float64

End time of the segment in seconds.

formatfloat
EventID string

The unique ID of the server event.

ItemID string

The ID of the item containing the input audio content.

Speaker string

The detected speaker label for this segment.

Start float64

Start time of the segment in seconds.

formatfloat
Text string

The text for this segment.

Type ConversationItemInputAudioTranscriptionSegment

The event type, must be conversation.item.input_audio_transcription.segment.

type ConversationItemRetrieveEvent struct{…}

Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. The server will respond with a conversation.item.retrieved event, unless the item does not exist in the conversation history, in which case the server will respond with an error.

ItemID string

The ID of the item to retrieve.

Type ConversationItemRetrieve

The event type, must be conversation.item.retrieve.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type ConversationItemTruncateEvent struct{…}

Send this event to truncate a previous assistant message’s audio. The server will produce audio faster than realtime, so this event is useful when the user interrupts to truncate audio that has already been sent to the client but not yet played. This will synchronize the server's understanding of the audio with the client's playback.

Truncating audio will delete the server-side text transcript to ensure there is not text in the context that hasn't been heard by the user.

If successful, the server will respond with a conversation.item.truncated event.

AudioEndMs int64

Inclusive duration up to which audio is truncated, in milliseconds. If the audio_end_ms is greater than the actual audio duration, the server will respond with an error.

ContentIndex int64

The index of the content part to truncate. Set this to 0.

ItemID string

The ID of the assistant message item to truncate. Only assistant message items can be truncated.

Type ConversationItemTruncate

The event type, must be conversation.item.truncate.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type ConversationItemTruncatedEvent struct{…}

Returned when an earlier assistant audio message item is truncated by the client with a conversation.item.truncate event. This event is used to synchronize the server's understanding of the audio with the client's playback.

This action will truncate the audio and remove the server-side text transcript to ensure there is no text in the context that hasn't been heard by the user.

AudioEndMs int64

The duration up to which the audio was truncated, in milliseconds.

ContentIndex int64

The index of the content part that was truncated.

EventID string

The unique ID of the server event.

ItemID string

The ID of the assistant message item that was truncated.

Type ConversationItemTruncated

The event type, must be conversation.item.truncated.

type ConversationItemWithReference struct{…}

The item to add to the conversation.

ID stringoptional

For an item of type (message | function_call | function_call_output) this field allows the client to assign the unique ID of the item. It is not required because the server will generate one if not provided.

For an item of type item_reference, this field is required and is a reference to any item that has previously existed in the conversation.

Arguments stringoptional

The arguments of the function call (for function_call items).

CallID stringoptional

The ID of the function call (for function_call and function_call_output items). If passed on a function_call_output item, the server will check that a function_call item with the same ID exists in the conversation history.

Content []ConversationItemWithReferenceContentoptional

The content of the message, applicable for message items.

  • Message items of role system support only input_text content
  • Message items of role user support input_text and input_audio content
  • Message items of role assistant support text content.
ID stringoptional

ID of a previous conversation item to reference (for item_reference content types in response.create events). These can reference both client and server created items.

Audio stringoptional

Base64-encoded audio bytes, used for input_audio content type.

Text stringoptional

The text content, used for input_text and text content types.

Transcript stringoptional

The transcript of the audio, used for input_audio content type.

Type stringoptional

The content type (input_text, input_audio, item_reference, text).

Accepts one of the following:
const ConversationItemWithReferenceContentTypeInputText ConversationItemWithReferenceContentType = "input_text"
const ConversationItemWithReferenceContentTypeInputAudio ConversationItemWithReferenceContentType = "input_audio"
const ConversationItemWithReferenceContentTypeItemReference ConversationItemWithReferenceContentType = "item_reference"
const ConversationItemWithReferenceContentTypeText ConversationItemWithReferenceContentType = "text"
Name stringoptional

The name of the function being called (for function_call items).

Object ConversationItemWithReferenceObjectoptional

Identifier for the API object being returned - always realtime.item.

Output stringoptional

The output of the function call (for function_call_output items).

Role ConversationItemWithReferenceRoleoptional

The role of the message sender (user, assistant, system), only applicable for message items.

Accepts one of the following:
const ConversationItemWithReferenceRoleUser ConversationItemWithReferenceRole = "user"
const ConversationItemWithReferenceRoleAssistant ConversationItemWithReferenceRole = "assistant"
const ConversationItemWithReferenceRoleSystem ConversationItemWithReferenceRole = "system"
Status ConversationItemWithReferenceStatusoptional

The status of the item (completed, incomplete, in_progress). These have no effect on the conversation, but are accepted for consistency with the conversation.item.created event.

Accepts one of the following:
const ConversationItemWithReferenceStatusCompleted ConversationItemWithReferenceStatus = "completed"
const ConversationItemWithReferenceStatusIncomplete ConversationItemWithReferenceStatus = "incomplete"
const ConversationItemWithReferenceStatusInProgress ConversationItemWithReferenceStatus = "in_progress"
Type ConversationItemWithReferenceTypeoptional

The type of the item (message, function_call, function_call_output, item_reference).

Accepts one of the following:
const ConversationItemWithReferenceTypeMessage ConversationItemWithReferenceType = "message"
const ConversationItemWithReferenceTypeFunctionCall ConversationItemWithReferenceType = "function_call"
const ConversationItemWithReferenceTypeFunctionCallOutput ConversationItemWithReferenceType = "function_call_output"
const ConversationItemWithReferenceTypeItemReference ConversationItemWithReferenceType = "item_reference"
type InputAudioBufferAppendEvent struct{…}

Send this event to append audio bytes to the input audio buffer. The audio buffer is temporary storage you can write to and later commit. A "commit" will create a new user message item in the conversation history from the buffer content and clear the buffer. Input audio transcription (if enabled) will be generated when the buffer is committed.

If VAD is enabled the audio buffer is used to detect speech and the server will decide when to commit. When Server VAD is disabled, you must commit the audio buffer manually. Input audio noise reduction operates on writes to the audio buffer.

The client may choose how much audio to place in each event up to a maximum of 15 MiB, for example streaming smaller chunks from the client may allow the VAD to be more responsive. Unlike most other client events, the server will not send a confirmation response to this event.

Audio string

Base64-encoded audio bytes. This must be in the format specified by the input_audio_format field in the session configuration.

Type InputAudioBufferAppend

The event type, must be input_audio_buffer.append.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type InputAudioBufferClearEvent struct{…}

Send this event to clear the audio bytes in the buffer. The server will respond with an input_audio_buffer.cleared event.

Type InputAudioBufferClear

The event type, must be input_audio_buffer.clear.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type InputAudioBufferClearedEvent struct{…}

Returned when the input audio buffer is cleared by the client with a input_audio_buffer.clear event.

EventID string

The unique ID of the server event.

Type InputAudioBufferCleared

The event type, must be input_audio_buffer.cleared.

type InputAudioBufferCommitEvent struct{…}

Send this event to commit the user input audio buffer, which will create a new user message item in the conversation. This event will produce an error if the input audio buffer is empty. When in Server VAD mode, the client does not need to send this event, the server will commit the audio buffer automatically.

Committing the input audio buffer will trigger input audio transcription (if enabled in session configuration), but it will not create a response from the model. The server will respond with an input_audio_buffer.committed event.

Type InputAudioBufferCommit

The event type, must be input_audio_buffer.commit.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type InputAudioBufferCommittedEvent struct{…}

Returned when an input audio buffer is committed, either by the client or automatically in server VAD mode. The item_id property is the ID of the user message item that will be created, thus a conversation.item.created event will also be sent to the client.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item that will be created.

Type InputAudioBufferCommitted

The event type, must be input_audio_buffer.committed.

PreviousItemID stringoptional

The ID of the preceding item after which the new item will be inserted. Can be null if the item has no predecessor.

type InputAudioBufferDtmfEventReceivedEvent struct{…}

SIP Only: Returned when an DTMF event is received. A DTMF event is a message that represents a telephone keypad press (0–9, *, #, A–D). The event property is the keypad that the user press. The received_at is the UTC Unix Timestamp that the server received the event.

Event string

The telephone keypad that was pressed by the user.

ReceivedAt int64

UTC Unix Timestamp when DTMF Event was received by server.

Type InputAudioBufferDtmfEventReceived

The event type, must be input_audio_buffer.dtmf_event_received.

type InputAudioBufferSpeechStartedEvent struct{…}

Sent by the server when in server_vad mode to indicate that speech has been detected in the audio buffer. This can happen any time audio is added to the buffer (unless speech is already detected). The client may want to use this event to interrupt audio playback or provide visual feedback to the user.

The client should expect to receive a input_audio_buffer.speech_stopped event when speech stops. The item_id property is the ID of the user message item that will be created when speech stops and will also be included in the input_audio_buffer.speech_stopped event (unless the client manually commits the audio buffer during VAD activation).

AudioStartMs int64

Milliseconds from the start of all audio written to the buffer during the session when speech was first detected. This will correspond to the beginning of audio sent to the model, and thus includes the prefix_padding_ms configured in the Session.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item that will be created when speech stops.

Type InputAudioBufferSpeechStarted

The event type, must be input_audio_buffer.speech_started.

type InputAudioBufferSpeechStoppedEvent struct{…}

Returned in server_vad mode when the server detects the end of speech in the audio buffer. The server will also send an conversation.item.created event with the user message item that is created from the audio buffer.

AudioEndMs int64

Milliseconds since the session started when speech stopped. This will correspond to the end of audio sent to the model, and thus includes the min_silence_duration_ms configured in the Session.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item that will be created.

Type InputAudioBufferSpeechStopped

The event type, must be input_audio_buffer.speech_stopped.

type InputAudioBufferTimeoutTriggered struct{…}

Returned when the Server VAD timeout is triggered for the input audio buffer. This is configured with idle_timeout_ms in the turn_detection settings of the session, and it indicates that there hasn't been any speech detected for the configured duration.

The audio_start_ms and audio_end_ms fields indicate the segment of audio after the last model response up to the triggering time, as an offset from the beginning of audio written to the input audio buffer. This means it demarcates the segment of audio that was silent and the difference between the start and end values will roughly match the configured timeout.

The empty audio will be committed to the conversation as an input_audio item (there will be a input_audio_buffer.committed event) and a model response will be generated. There may be speech that didn't trigger VAD but is still detected by the model, so the model may respond with something relevant to the conversation or a prompt to continue speaking.

AudioEndMs int64

Millisecond offset of audio written to the input audio buffer at the time the timeout was triggered.

AudioStartMs int64

Millisecond offset of audio written to the input audio buffer that was after the playback time of the last model response.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item associated with this segment.

Type InputAudioBufferTimeoutTriggered

The event type, must be input_audio_buffer.timeout_triggered.

type LogProbProperties struct{…}

A log probability object.

Token string

The token that was used to generate the log probability.

Bytes []int64

The bytes that were used to generate the log probability.

Logprob float64

The log probability of the token.

type McpListToolsCompleted struct{…}

Returned when listing MCP tools has completed for an item.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP list tools item.

Type McpListToolsCompleted

The event type, must be mcp_list_tools.completed.

type McpListToolsFailed struct{…}

Returned when listing MCP tools has failed for an item.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP list tools item.

Type McpListToolsFailed

The event type, must be mcp_list_tools.failed.

type McpListToolsInProgress struct{…}

Returned when listing MCP tools is in progress for an item.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP list tools item.

Type McpListToolsInProgress

The event type, must be mcp_list_tools.in_progress.

type NoiseReductionType string

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

Accepts one of the following:
const NoiseReductionTypeNearField NoiseReductionType = "near_field"
const NoiseReductionTypeFarField NoiseReductionType = "far_field"
type OutputAudioBufferClearEvent struct{…}

WebRTC/SIP Only: Emit to cut off the current audio response. This will trigger the server to stop generating audio and emit a output_audio_buffer.cleared event. This event should be preceded by a response.cancel client event to stop the generation of the current response. Learn more.

Type OutputAudioBufferClear

The event type, must be output_audio_buffer.clear.

EventID stringoptional

The unique ID of the client event used for error handling.

type RateLimitsUpdatedEvent struct{…}

Emitted at the beginning of a Response to indicate the updated rate limits. When a Response is created some tokens will be "reserved" for the output tokens, the rate limits shown here reflect that reservation, which is then adjusted accordingly once the Response is completed.

EventID string

The unique ID of the server event.

RateLimits []RateLimitsUpdatedEventRateLimit

List of rate limit information.

Limit int64optional

The maximum allowed value for the rate limit.

Name stringoptional

The name of the rate limit (requests, tokens).

Accepts one of the following:
const RateLimitsUpdatedEventRateLimitNameRequests RateLimitsUpdatedEventRateLimitName = "requests"
const RateLimitsUpdatedEventRateLimitNameTokens RateLimitsUpdatedEventRateLimitName = "tokens"
Remaining int64optional

The remaining value before the limit is reached.

ResetSeconds float64optional

Seconds until the rate limit resets.

Type RateLimitsUpdated

The event type, must be rate_limits.updated.

type RealtimeAudioConfig struct{…}

Configuration for input and output audio.

type RealtimeAudioConfigInput struct{…}

The format of the input audio.

NoiseReduction RealtimeAudioConfigInputNoiseReductionoptional

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Type NoiseReductionTypeoptional

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

Transcription AudioTranscriptionoptional

Configuration for input audio transcription, defaults to off and can be set to null to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through the /audio/transcriptions endpoint and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

type RealtimeAudioConfigOutput struct{…}

The format of the output audio.

Speed float64optional

The speed of the model's spoken response as a multiple of the original speed. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.

This parameter is a post-processing adjustment to the audio after it is generated, it's also possible to prompt the model to speak faster or slower.

maximum1.5
minimum0.25
Voice RealtimeAudioConfigOutputVoiceoptional

The voice the model uses to respond. Supported built-in voices are alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, and cedar. Voice cannot be changed during the session once the model has responded with audio at least once. We recommend marin and cedar for best quality.

Accepts one of the following:
string
RealtimeAudioConfigOutputVoice
Accepts one of the following:
const RealtimeAudioConfigOutputVoiceAlloy RealtimeAudioConfigOutputVoice = "alloy"
const RealtimeAudioConfigOutputVoiceAsh RealtimeAudioConfigOutputVoice = "ash"
const RealtimeAudioConfigOutputVoiceBallad RealtimeAudioConfigOutputVoice = "ballad"
const RealtimeAudioConfigOutputVoiceCoral RealtimeAudioConfigOutputVoice = "coral"
const RealtimeAudioConfigOutputVoiceEcho RealtimeAudioConfigOutputVoice = "echo"
const RealtimeAudioConfigOutputVoiceSage RealtimeAudioConfigOutputVoice = "sage"
const RealtimeAudioConfigOutputVoiceShimmer RealtimeAudioConfigOutputVoice = "shimmer"
const RealtimeAudioConfigOutputVoiceVerse RealtimeAudioConfigOutputVoice = "verse"
const RealtimeAudioConfigOutputVoiceMarin RealtimeAudioConfigOutputVoice = "marin"
const RealtimeAudioConfigOutputVoiceCedar RealtimeAudioConfigOutputVoice = "cedar"
type RealtimeAudioFormatsUnion interface{…}

The PCM audio format. Only a 24kHz sample rate is supported.

Accepts one of the following:
type RealtimeAudioFormatsAudioPCM struct{…}

The PCM audio format. Only a 24kHz sample rate is supported.

Rate int64optional

The sample rate of the audio. Always 24000.

Type stringoptional

The audio format. Always audio/pcm.

type RealtimeAudioFormatsAudioPCMU struct{…}

The G.711 μ-law format.

Type stringoptional

The audio format. Always audio/pcmu.

type RealtimeAudioFormatsAudioPCMA struct{…}

The G.711 A-law format.

Type stringoptional

The audio format. Always audio/pcma.

type RealtimeAudioInputTurnDetectionUnion interface{…}

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

Accepts one of the following:
RealtimeAudioInputTurnDetectionServerVad
Type ServerVad

Type of turn detection, server_vad to turn on simple Server VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs. If interrupt_response is set to false this may fail to create a response if the model is already responding.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

IdleTimeoutMs int64optional

Optional timeout after which a model response will be triggered automatically. This is useful for situations in which a long pause from the user is unexpected, such as a phone call. The model will effectively prompt the user to continue the conversation based on the current context.

The timeout value will be applied after the last model response's audio has finished playing, i.e. it's set to the response.done time plus audio playback duration.

An input_audio_buffer.timeout_triggered event (plus events associated with the Response) will be emitted when the timeout is reached. Idle timeout is currently only supported for server_vad mode.

minimum5000
maximum30000
InterruptResponse booloptional

Whether or not to automatically interrupt (cancel) any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs. If true then the response will be cancelled, otherwise it will continue until complete.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

PrefixPaddingMs int64optional

Used only for server_vad mode. Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

SilenceDurationMs int64optional

Used only for server_vad mode. Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Threshold float64optional

Used only for server_vad mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

RealtimeAudioInputTurnDetectionSemanticVad
Type SemanticVad

Type of turn detection, semantic_vad to turn on Semantic VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs.

Eagerness stringoptional

Used only for semantic_vad mode. The eagerness of the model to respond. low will wait longer for the user to continue speaking, high will respond more quickly. auto is the default and is equivalent to medium. low, medium, and high have max timeouts of 8s, 4s, and 2s respectively.

Accepts one of the following:
const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"
const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"
const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"
const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"
InterruptResponse booloptional

Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs.

type RealtimeClientEventUnion interface{…}

A realtime client event.

Accepts one of the following:
type ConversationItemCreateEvent struct{…}

Add a new Item to the Conversation's context, including messages, function calls, and function call responses. This event can be used both to populate a "history" of the conversation and to add new items mid-stream, but has the current limitation that it cannot populate assistant audio messages.

If successful, the server will respond with a conversation.item.created event, otherwise an error event will be sent.

A single item within a Realtime conversation.

Type ConversationItemCreate

The event type, must be conversation.item.create.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
PreviousItemID stringoptional

The ID of the preceding item after which the new item will be inserted. If not set, the new item will be appended to the end of the conversation.

If set to root, the new item will be added to the beginning of the conversation.

If set to an existing ID, it allows an item to be inserted mid-conversation. If the ID cannot be found, an error will be returned and the item will not be added.

type ConversationItemDeleteEvent struct{…}

Send this event when you want to remove any item from the conversation history. The server will respond with a conversation.item.deleted event, unless the item does not exist in the conversation history, in which case the server will respond with an error.

ItemID string

The ID of the item to delete.

Type ConversationItemDelete

The event type, must be conversation.item.delete.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type ConversationItemRetrieveEvent struct{…}

Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. The server will respond with a conversation.item.retrieved event, unless the item does not exist in the conversation history, in which case the server will respond with an error.

ItemID string

The ID of the item to retrieve.

Type ConversationItemRetrieve

The event type, must be conversation.item.retrieve.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type ConversationItemTruncateEvent struct{…}

Send this event to truncate a previous assistant message’s audio. The server will produce audio faster than realtime, so this event is useful when the user interrupts to truncate audio that has already been sent to the client but not yet played. This will synchronize the server's understanding of the audio with the client's playback.

Truncating audio will delete the server-side text transcript to ensure there is not text in the context that hasn't been heard by the user.

If successful, the server will respond with a conversation.item.truncated event.

AudioEndMs int64

Inclusive duration up to which audio is truncated, in milliseconds. If the audio_end_ms is greater than the actual audio duration, the server will respond with an error.

ContentIndex int64

The index of the content part to truncate. Set this to 0.

ItemID string

The ID of the assistant message item to truncate. Only assistant message items can be truncated.

Type ConversationItemTruncate

The event type, must be conversation.item.truncate.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type InputAudioBufferAppendEvent struct{…}

Send this event to append audio bytes to the input audio buffer. The audio buffer is temporary storage you can write to and later commit. A "commit" will create a new user message item in the conversation history from the buffer content and clear the buffer. Input audio transcription (if enabled) will be generated when the buffer is committed.

If VAD is enabled the audio buffer is used to detect speech and the server will decide when to commit. When Server VAD is disabled, you must commit the audio buffer manually. Input audio noise reduction operates on writes to the audio buffer.

The client may choose how much audio to place in each event up to a maximum of 15 MiB, for example streaming smaller chunks from the client may allow the VAD to be more responsive. Unlike most other client events, the server will not send a confirmation response to this event.

Audio string

Base64-encoded audio bytes. This must be in the format specified by the input_audio_format field in the session configuration.

Type InputAudioBufferAppend

The event type, must be input_audio_buffer.append.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type InputAudioBufferClearEvent struct{…}

Send this event to clear the audio bytes in the buffer. The server will respond with an input_audio_buffer.cleared event.

Type InputAudioBufferClear

The event type, must be input_audio_buffer.clear.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type OutputAudioBufferClearEvent struct{…}

WebRTC/SIP Only: Emit to cut off the current audio response. This will trigger the server to stop generating audio and emit a output_audio_buffer.cleared event. This event should be preceded by a response.cancel client event to stop the generation of the current response. Learn more.

Type OutputAudioBufferClear

The event type, must be output_audio_buffer.clear.

EventID stringoptional

The unique ID of the client event used for error handling.

type InputAudioBufferCommitEvent struct{…}

Send this event to commit the user input audio buffer, which will create a new user message item in the conversation. This event will produce an error if the input audio buffer is empty. When in Server VAD mode, the client does not need to send this event, the server will commit the audio buffer automatically.

Committing the input audio buffer will trigger input audio transcription (if enabled in session configuration), but it will not create a response from the model. The server will respond with an input_audio_buffer.committed event.

Type InputAudioBufferCommit

The event type, must be input_audio_buffer.commit.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
type ResponseCancelEvent struct{…}

Send this event to cancel an in-progress response. The server will respond with a response.done event with a status of response.status=cancelled. If there is no response to cancel, the server will respond with an error. It's safe to call response.cancel even if no response is in progress, an error will be returned the session will remain unaffected.

Type ResponseCancel

The event type, must be response.cancel.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
ResponseID stringoptional

A specific response ID to cancel - if not provided, will cancel an in-progress response in the default conversation.

type ResponseCreateEvent struct{…}

This event instructs the server to create a Response, which means triggering model inference. When in Server VAD mode, the server will create Responses automatically.

A Response will include at least one Item, and may have two, in which case the second will be a function call. These Items will be appended to the conversation history by default.

The server will respond with a response.created event, events for Items and content created, and finally a response.done event to indicate the Response is complete.

The response.create event includes inference configuration like instructions and tools. If these are set, they will override the Session's configuration for this Response only.

Responses can be created out-of-band of the default Conversation, meaning that they can have arbitrary input, and it's possible to disable writing the output to the Conversation. Only one Response can write to the default Conversation at a time, but otherwise multiple Responses can be created in parallel. The metadata field is a good way to disambiguate multiple simultaneous Responses.

Clients can set conversation to none to create a Response that does not write to the default Conversation. Arbitrary input can be provided with the input field, which is an array accepting raw Items and references to existing Items.

Type ResponseCreate

The event type, must be response.create.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512

Create a new Realtime response with these parameters

type SessionUpdateEvent struct{…}

Send this event to update the session’s configuration. The client may send this event at any time to update any field except for voice and model. voice can be updated only if there have been no other audio outputs yet.

When the server receives a session.update, it will respond with a session.updated event showing the full, effective configuration. Only the fields that are present in the session.update are updated. To clear a field like instructions, pass an empty string. To clear a field like tools, pass an empty array. To clear a field like turn_detection, pass null.

Session SessionUpdateEventSessionUnion

Update the Realtime session. Choose either a realtime session or a transcription session.

Accepts one of the following:
type RealtimeSessionCreateRequest struct{…}

Realtime session object configuration.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeAudioConfigoptional

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Model RealtimeSessionCreateRequestModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionCreateRequestModel
Accepts one of the following:
const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"
const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"
const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Tools RealtimeToolsConfigoptional

Tools available to the model.

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeTranscriptionSessionCreateRequest struct{…}

Realtime transcription session object configuration.

Type Transcription

The type of session to create. Always transcription for transcription sessions.

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Type SessionUpdate

The event type, must be session.update.

EventID stringoptional

Optional client-generated ID used to identify this event. This is an arbitrary string that a client may assign. It will be passed back if there is an error with the event, but the corresponding session.updated event will not include it.

maxLength512
type RealtimeConversationItemAssistantMessage struct{…}

An assistant message item in a Realtime conversation.

Content []RealtimeConversationItemAssistantMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Text stringoptional

The text content.

Transcript stringoptional

The transcript of the audio content, this will always be present if the output type is audio.

Type stringoptional

The content type, output_text or output_audio depending on the session output_modalities configuration.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"
const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"
Role Assistant

The role of the message sender. Always assistant.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemAssistantMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemAssistantMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"
const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"
const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"
type RealtimeConversationItemFunctionCall struct{…}

A function call item in a Realtime conversation.

Arguments string

The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example {"arg1": "value1", "arg2": 42}.

Name string

The name of the function being called.

Type FunctionCall

The type of the item. Always function_call.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

CallID stringoptional

The ID of the function call.

Object RealtimeConversationItemFunctionCallObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"
const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"
const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"
type RealtimeConversationItemFunctionCallOutput struct{…}

A function call output item in a Realtime conversation.

CallID string

The ID of the function call this output is for.

Output string

The output of the function call, this is free text and can contain any information or simply be empty.

Type FunctionCallOutput

The type of the item. Always function_call_output.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemFunctionCallOutputObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallOutputStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"
const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"
const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"
type RealtimeConversationItemSystemMessage struct{…}

A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages.

Content []RealtimeConversationItemSystemMessageContent

The content of the message.

Text stringoptional

The text content.

Type stringoptional

The content type. Always input_text for system messages.

Role System

The role of the message sender. Always system.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemSystemMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemSystemMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"
const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"
const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"
type RealtimeConversationItemUserMessage struct{…}

A user message item in a Realtime conversation.

Content []RealtimeConversationItemUserMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes (for input_audio), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Detail stringoptional

The detail level of the image (for input_image). auto will default to high.

Accepts one of the following:
const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"
const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"
const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"
ImageURL stringoptional

Base64-encoded image bytes (for input_image) as a data URI. For example data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA.... Supported formats are PNG and JPEG.

Text stringoptional

The text content (for input_text).

Transcript stringoptional

Transcript of the audio (for input_audio). This is not sent to the model, but will be attached to the message item for reference.

Type stringoptional

The content type (input_text, input_audio, or input_image).

Accepts one of the following:
const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"
const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"
const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"
Role User

The role of the message sender. Always user.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemUserMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemUserMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"
const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"
const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"
type RealtimeError struct{…}

Details of the error.

Message string

A human-readable error message.

Type string

The type of error (e.g., "invalid_request_error", "server_error").

Code stringoptional

Error code, if any.

EventID stringoptional

The event_id of the client event that caused the error, if applicable.

Param stringoptional

Parameter related to the error, if any.

type RealtimeErrorEvent struct{…}

Returned when an error occurs, which could be a client problem or a server problem. Most errors are recoverable and the session will stay open, we recommend to implementors to monitor and log error messages by default.

Details of the error.

EventID string

The unique ID of the server event.

Type Error

The event type, must be error.

type RealtimeFunctionTool struct{…}
Description stringoptional

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

Name stringoptional

The name of the function.

Parameters anyoptional

Parameters of the function in JSON Schema.

Type RealtimeFunctionToolTypeoptional

The type of the tool, i.e. function.

type RealtimeMcpApprovalRequest struct{…}

A Realtime item requesting human approval of a tool invocation.

ID string

The unique ID of the approval request.

Arguments string

A JSON string of arguments for the tool.

Name string

The name of the tool to run.

ServerLabel string

The label of the MCP server making the request.

Type McpApprovalRequest

The type of the item. Always mcp_approval_request.

type RealtimeMcpApprovalResponse struct{…}

A Realtime item responding to an MCP approval request.

ID string

The unique ID of the approval response.

ApprovalRequestID string

The ID of the approval request being answered.

Approve bool

Whether the request was approved.

Type McpApprovalResponse

The type of the item. Always mcp_approval_response.

Reason stringoptional

Optional reason for the decision.

type RealtimeMcpListTools struct{…}

A Realtime item listing tools available on an MCP server.

ServerLabel string

The label of the MCP server.

Tools []RealtimeMcpListToolsTool

The tools available on the server.

InputSchema any

The JSON schema describing the tool's input.

Name string

The name of the tool.

Annotations anyoptional

Additional annotations about the tool.

Description stringoptional

The description of the tool.

Type McpListTools

The type of the item. Always mcp_list_tools.

ID stringoptional

The unique ID of the list.

type RealtimeMcpProtocolError struct{…}
Code int64
Message string
Type ProtocolError
type RealtimeMcpToolCall struct{…}

A Realtime item representing an invocation of a tool on an MCP server.

ID string

The unique ID of the tool call.

Arguments string

A JSON string of the arguments passed to the tool.

Name string

The name of the tool that was run.

ServerLabel string

The label of the MCP server running the tool.

Type McpCall

The type of the item. Always mcp_call.

ApprovalRequestID stringoptional

The ID of an associated approval request, if any.

Error RealtimeMcpToolCallErrorUnionoptional

The error from the tool call, if any.

Accepts one of the following:
type RealtimeMcpProtocolError struct{…}
Code int64
Message string
Type ProtocolError
type RealtimeMcpToolExecutionError struct{…}
Message string
Type ToolExecutionError
type RealtimeMcphttpError struct{…}
Code int64
Message string
Type HTTPError
Output stringoptional

The output from the tool call.

type RealtimeMcpToolExecutionError struct{…}
Message string
Type ToolExecutionError
type RealtimeMcphttpError struct{…}
Code int64
Message string
Type HTTPError
type RealtimeResponse struct{…}

The response resource.

ID stringoptional

The unique ID of the response, will look like resp_1234.

Audio RealtimeResponseAudiooptional

Configuration for audio output.

Output RealtimeResponseAudioOutputoptional

The format of the output audio.

Voice stringoptional

The voice the model uses to respond. Voice cannot be changed during the session once the model has responded with audio at least once. Current voice options are alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, and cedar. We recommend marin and cedar for best quality.

Accepts one of the following:
string
string
Accepts one of the following:
const RealtimeResponseAudioOutputVoiceAlloy RealtimeResponseAudioOutputVoice = "alloy"
const RealtimeResponseAudioOutputVoiceAsh RealtimeResponseAudioOutputVoice = "ash"
const RealtimeResponseAudioOutputVoiceBallad RealtimeResponseAudioOutputVoice = "ballad"
const RealtimeResponseAudioOutputVoiceCoral RealtimeResponseAudioOutputVoice = "coral"
const RealtimeResponseAudioOutputVoiceEcho RealtimeResponseAudioOutputVoice = "echo"
const RealtimeResponseAudioOutputVoiceSage RealtimeResponseAudioOutputVoice = "sage"
const RealtimeResponseAudioOutputVoiceShimmer RealtimeResponseAudioOutputVoice = "shimmer"
const RealtimeResponseAudioOutputVoiceVerse RealtimeResponseAudioOutputVoice = "verse"
const RealtimeResponseAudioOutputVoiceMarin RealtimeResponseAudioOutputVoice = "marin"
const RealtimeResponseAudioOutputVoiceCedar RealtimeResponseAudioOutputVoice = "cedar"
ConversationID stringoptional

Which conversation the response is added to, determined by the conversation field in the response.create event. If auto, the response will be added to the default conversation and the value of conversation_id will be an id like conv_1234. If none, the response will not be added to any conversation and the value of conversation_id will be null. If responses are being triggered automatically by VAD the response will be added to the default conversation

MaxOutputTokens RealtimeResponseMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls, that was used in this response.

Accepts one of the following:
int64
Inf
Metadata Metadataoptional

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Object RealtimeResponseObjectoptional

The object type, must be realtime.response.

Output []ConversationItemUnionoptional

The list of output items generated by the response.

Accepts one of the following:
type RealtimeConversationItemSystemMessage struct{…}

A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages.

Content []RealtimeConversationItemSystemMessageContent

The content of the message.

Text stringoptional

The text content.

Type stringoptional

The content type. Always input_text for system messages.

Role System

The role of the message sender. Always system.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemSystemMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemSystemMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"
const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"
const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"
type RealtimeConversationItemUserMessage struct{…}

A user message item in a Realtime conversation.

Content []RealtimeConversationItemUserMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes (for input_audio), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Detail stringoptional

The detail level of the image (for input_image). auto will default to high.

Accepts one of the following:
const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"
const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"
const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"
ImageURL stringoptional

Base64-encoded image bytes (for input_image) as a data URI. For example data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA.... Supported formats are PNG and JPEG.

Text stringoptional

The text content (for input_text).

Transcript stringoptional

Transcript of the audio (for input_audio). This is not sent to the model, but will be attached to the message item for reference.

Type stringoptional

The content type (input_text, input_audio, or input_image).

Accepts one of the following:
const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"
const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"
const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"
Role User

The role of the message sender. Always user.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemUserMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemUserMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"
const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"
const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"
type RealtimeConversationItemAssistantMessage struct{…}

An assistant message item in a Realtime conversation.

Content []RealtimeConversationItemAssistantMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Text stringoptional

The text content.

Transcript stringoptional

The transcript of the audio content, this will always be present if the output type is audio.

Type stringoptional

The content type, output_text or output_audio depending on the session output_modalities configuration.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"
const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"
Role Assistant

The role of the message sender. Always assistant.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemAssistantMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemAssistantMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"
const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"
const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"
type RealtimeConversationItemFunctionCall struct{…}

A function call item in a Realtime conversation.

Arguments string

The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example {"arg1": "value1", "arg2": 42}.

Name string

The name of the function being called.

Type FunctionCall

The type of the item. Always function_call.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

CallID stringoptional

The ID of the function call.

Object RealtimeConversationItemFunctionCallObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"
const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"
const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"
type RealtimeConversationItemFunctionCallOutput struct{…}

A function call output item in a Realtime conversation.

CallID string

The ID of the function call this output is for.

Output string

The output of the function call, this is free text and can contain any information or simply be empty.

Type FunctionCallOutput

The type of the item. Always function_call_output.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemFunctionCallOutputObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallOutputStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"
const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"
const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"
type RealtimeMcpApprovalResponse struct{…}

A Realtime item responding to an MCP approval request.

ID string

The unique ID of the approval response.

ApprovalRequestID string

The ID of the approval request being answered.

Approve bool

Whether the request was approved.

Type McpApprovalResponse

The type of the item. Always mcp_approval_response.

Reason stringoptional

Optional reason for the decision.

type RealtimeMcpListTools struct{…}

A Realtime item listing tools available on an MCP server.

ServerLabel string

The label of the MCP server.

Tools []RealtimeMcpListToolsTool

The tools available on the server.

InputSchema any

The JSON schema describing the tool's input.

Name string

The name of the tool.

Annotations anyoptional

Additional annotations about the tool.

Description stringoptional

The description of the tool.

Type McpListTools

The type of the item. Always mcp_list_tools.

ID stringoptional

The unique ID of the list.

type RealtimeMcpToolCall struct{…}

A Realtime item representing an invocation of a tool on an MCP server.

ID string

The unique ID of the tool call.

Arguments string

A JSON string of the arguments passed to the tool.

Name string

The name of the tool that was run.

ServerLabel string

The label of the MCP server running the tool.

Type McpCall

The type of the item. Always mcp_call.

ApprovalRequestID stringoptional

The ID of an associated approval request, if any.

Error RealtimeMcpToolCallErrorUnionoptional

The error from the tool call, if any.

Accepts one of the following:
type RealtimeMcpProtocolError struct{…}
Code int64
Message string
Type ProtocolError
type RealtimeMcpToolExecutionError struct{…}
Message string
Type ToolExecutionError
type RealtimeMcphttpError struct{…}
Code int64
Message string
Type HTTPError
Output stringoptional

The output from the tool call.

type RealtimeMcpApprovalRequest struct{…}

A Realtime item requesting human approval of a tool invocation.

ID string

The unique ID of the approval request.

Arguments string

A JSON string of arguments for the tool.

Name string

The name of the tool to run.

ServerLabel string

The label of the MCP server making the request.

Type McpApprovalRequest

The type of the item. Always mcp_approval_request.

OutputModalities []stringoptional

The set of modalities the model used to respond, currently the only possible values are [\"audio\"], [\"text\"]. Audio output always include a text transcript. Setting the output to mode text will disable audio output from the model.

Accepts one of the following:
const RealtimeResponseOutputModalityText RealtimeResponseOutputModality = "text"
const RealtimeResponseOutputModalityAudio RealtimeResponseOutputModality = "audio"
Status RealtimeResponseStatusoptional

The final status of the response (completed, cancelled, failed, or incomplete, in_progress).

Accepts one of the following:
const RealtimeResponseStatusCompleted RealtimeResponseStatus = "completed"
const RealtimeResponseStatusCancelled RealtimeResponseStatus = "cancelled"
const RealtimeResponseStatusFailed RealtimeResponseStatus = "failed"
const RealtimeResponseStatusIncomplete RealtimeResponseStatus = "incomplete"
const RealtimeResponseStatusInProgress RealtimeResponseStatus = "in_progress"
StatusDetails RealtimeResponseStatusoptional

Additional details about the status.

Usage RealtimeResponseUsageoptional

Usage statistics for the Response, this will correspond to billing. A Realtime API session will maintain a conversation context and append new Items to the Conversation, thus output from previous turns (text and audio tokens) will become the input for later turns.

type RealtimeResponseCreateAudioOutput struct{…}

Configuration for audio input and output.

Output RealtimeResponseCreateAudioOutputOutputoptional

The format of the output audio.

Voice stringoptional

The voice the model uses to respond. Supported built-in voices are alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, and cedar. Voice cannot be changed during the session once the model has responded with audio at least once.

Accepts one of the following:
string
string
Accepts one of the following:
const RealtimeResponseCreateAudioOutputOutputVoiceAlloy RealtimeResponseCreateAudioOutputOutputVoice = "alloy"
const RealtimeResponseCreateAudioOutputOutputVoiceAsh RealtimeResponseCreateAudioOutputOutputVoice = "ash"
const RealtimeResponseCreateAudioOutputOutputVoiceBallad RealtimeResponseCreateAudioOutputOutputVoice = "ballad"
const RealtimeResponseCreateAudioOutputOutputVoiceCoral RealtimeResponseCreateAudioOutputOutputVoice = "coral"
const RealtimeResponseCreateAudioOutputOutputVoiceEcho RealtimeResponseCreateAudioOutputOutputVoice = "echo"
const RealtimeResponseCreateAudioOutputOutputVoiceSage RealtimeResponseCreateAudioOutputOutputVoice = "sage"
const RealtimeResponseCreateAudioOutputOutputVoiceShimmer RealtimeResponseCreateAudioOutputOutputVoice = "shimmer"
const RealtimeResponseCreateAudioOutputOutputVoiceVerse RealtimeResponseCreateAudioOutputOutputVoice = "verse"
const RealtimeResponseCreateAudioOutputOutputVoiceMarin RealtimeResponseCreateAudioOutputOutputVoice = "marin"
const RealtimeResponseCreateAudioOutputOutputVoiceCedar RealtimeResponseCreateAudioOutputOutputVoice = "cedar"
type RealtimeResponseCreateMcpTool struct{…}

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

ServerLabel string

A label for this MCP server, used to identify it in tool calls.

Type Mcp

The type of the MCP tool. Always mcp.

AllowedTools RealtimeResponseCreateMcpToolAllowedToolsUnionoptional

List of allowed tool names or a filter object.

Accepts one of the following:
[]string
RealtimeResponseCreateMcpToolAllowedToolsMcpToolFilter
ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Authorization stringoptional

An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.

ConnectorID RealtimeResponseCreateMcpToolConnectorIDoptional

Identifier for service connectors, like those available in ChatGPT. One of server_url or connector_id must be provided. Learn more about service connectors here.

Currently supported connector_id values are:

  • Dropbox: connector_dropbox
  • Gmail: connector_gmail
  • Google Calendar: connector_googlecalendar
  • Google Drive: connector_googledrive
  • Microsoft Teams: connector_microsoftteams
  • Outlook Calendar: connector_outlookcalendar
  • Outlook Email: connector_outlookemail
  • SharePoint: connector_sharepoint
Accepts one of the following:
const RealtimeResponseCreateMcpToolConnectorIDConnectorDropbox RealtimeResponseCreateMcpToolConnectorID = "connector_dropbox"
const RealtimeResponseCreateMcpToolConnectorIDConnectorGmail RealtimeResponseCreateMcpToolConnectorID = "connector_gmail"
const RealtimeResponseCreateMcpToolConnectorIDConnectorGooglecalendar RealtimeResponseCreateMcpToolConnectorID = "connector_googlecalendar"
const RealtimeResponseCreateMcpToolConnectorIDConnectorGoogledrive RealtimeResponseCreateMcpToolConnectorID = "connector_googledrive"
const RealtimeResponseCreateMcpToolConnectorIDConnectorMicrosoftteams RealtimeResponseCreateMcpToolConnectorID = "connector_microsoftteams"
const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookcalendar RealtimeResponseCreateMcpToolConnectorID = "connector_outlookcalendar"
const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookemail RealtimeResponseCreateMcpToolConnectorID = "connector_outlookemail"
const RealtimeResponseCreateMcpToolConnectorIDConnectorSharepoint RealtimeResponseCreateMcpToolConnectorID = "connector_sharepoint"
Headers map[string, string]optional

Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.

RequireApproval RealtimeResponseCreateMcpToolRequireApprovalUnionoptional

Specify which of the MCP server's tools require approval.

Accepts one of the following:
RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilter
Always RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterAlwaysoptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Never RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterNeveroptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

string
Accepts one of the following:
const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "always"
const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "never"
ServerDescription stringoptional

Optional description of the MCP server, used to provide more context.

ServerURL stringoptional

The URL for the MCP server. One of server_url or connector_id must be provided.

type RealtimeResponseCreateParamsResp struct{…}

Create a new Realtime response with these parameters

Configuration for audio input and output.

Conversation RealtimeResponseCreateParamsConversationoptional

Controls which conversation the response is added to. Currently supports auto and none, with auto as the default value. The auto value means that the contents of the response will be added to the default conversation. Set this to none to create an out-of-band response which will not add items to default conversation.

Accepts one of the following:
string
RealtimeResponseCreateParamsConversation
Accepts one of the following:
const RealtimeResponseCreateParamsConversationAuto RealtimeResponseCreateParamsConversation = "auto"
const RealtimeResponseCreateParamsConversationNone RealtimeResponseCreateParamsConversation = "none"
Input []ConversationItemUnionoptional

Input items to include in the prompt for the model. Using this field creates a new context for this Response instead of using the default conversation. An empty array [] will clear the context for this Response. Note that this can include references to items that previously appeared in the session using their id.

Accepts one of the following:
type RealtimeConversationItemSystemMessage struct{…}

A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages.

Content []RealtimeConversationItemSystemMessageContent

The content of the message.

Text stringoptional

The text content.

Type stringoptional

The content type. Always input_text for system messages.

Role System

The role of the message sender. Always system.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemSystemMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemSystemMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"
const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"
const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"
type RealtimeConversationItemUserMessage struct{…}

A user message item in a Realtime conversation.

Content []RealtimeConversationItemUserMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes (for input_audio), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Detail stringoptional

The detail level of the image (for input_image). auto will default to high.

Accepts one of the following:
const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"
const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"
const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"
ImageURL stringoptional

Base64-encoded image bytes (for input_image) as a data URI. For example data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA.... Supported formats are PNG and JPEG.

Text stringoptional

The text content (for input_text).

Transcript stringoptional

Transcript of the audio (for input_audio). This is not sent to the model, but will be attached to the message item for reference.

Type stringoptional

The content type (input_text, input_audio, or input_image).

Accepts one of the following:
const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"
const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"
const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"
Role User

The role of the message sender. Always user.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemUserMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemUserMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"
const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"
const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"
type RealtimeConversationItemAssistantMessage struct{…}

An assistant message item in a Realtime conversation.

Content []RealtimeConversationItemAssistantMessageContent

The content of the message.

Audio stringoptional

Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Text stringoptional

The text content.

Transcript stringoptional

The transcript of the audio content, this will always be present if the output type is audio.

Type stringoptional

The content type, output_text or output_audio depending on the session output_modalities configuration.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"
const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"
Role Assistant

The role of the message sender. Always assistant.

Type Message

The type of the item. Always message.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemAssistantMessageObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemAssistantMessageStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"
const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"
const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"
type RealtimeConversationItemFunctionCall struct{…}

A function call item in a Realtime conversation.

Arguments string

The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example {"arg1": "value1", "arg2": 42}.

Name string

The name of the function being called.

Type FunctionCall

The type of the item. Always function_call.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

CallID stringoptional

The ID of the function call.

Object RealtimeConversationItemFunctionCallObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"
const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"
const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"
type RealtimeConversationItemFunctionCallOutput struct{…}

A function call output item in a Realtime conversation.

CallID string

The ID of the function call this output is for.

Output string

The output of the function call, this is free text and can contain any information or simply be empty.

Type FunctionCallOutput

The type of the item. Always function_call_output.

ID stringoptional

The unique ID of the item. This may be provided by the client or generated by the server.

Object RealtimeConversationItemFunctionCallOutputObjectoptional

Identifier for the API object being returned - always realtime.item. Optional when creating a new item.

Status RealtimeConversationItemFunctionCallOutputStatusoptional

The status of the item. Has no effect on the conversation.

Accepts one of the following:
const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"
const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"
const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"
type RealtimeMcpApprovalResponse struct{…}

A Realtime item responding to an MCP approval request.

ID string

The unique ID of the approval response.

ApprovalRequestID string

The ID of the approval request being answered.

Approve bool

Whether the request was approved.

Type McpApprovalResponse

The type of the item. Always mcp_approval_response.

Reason stringoptional

Optional reason for the decision.

type RealtimeMcpListTools struct{…}

A Realtime item listing tools available on an MCP server.

ServerLabel string

The label of the MCP server.

Tools []RealtimeMcpListToolsTool

The tools available on the server.

InputSchema any

The JSON schema describing the tool's input.

Name string

The name of the tool.

Annotations anyoptional

Additional annotations about the tool.

Description stringoptional

The description of the tool.

Type McpListTools

The type of the item. Always mcp_list_tools.

ID stringoptional

The unique ID of the list.

type RealtimeMcpToolCall struct{…}

A Realtime item representing an invocation of a tool on an MCP server.

ID string

The unique ID of the tool call.

Arguments string

A JSON string of the arguments passed to the tool.

Name string

The name of the tool that was run.

ServerLabel string

The label of the MCP server running the tool.

Type McpCall

The type of the item. Always mcp_call.

ApprovalRequestID stringoptional

The ID of an associated approval request, if any.

Error RealtimeMcpToolCallErrorUnionoptional

The error from the tool call, if any.

Accepts one of the following:
type RealtimeMcpProtocolError struct{…}
Code int64
Message string
Type ProtocolError
type RealtimeMcpToolExecutionError struct{…}
Message string
Type ToolExecutionError
type RealtimeMcphttpError struct{…}
Code int64
Message string
Type HTTPError
Output stringoptional

The output from the tool call.

type RealtimeMcpApprovalRequest struct{…}

A Realtime item requesting human approval of a tool invocation.

ID string

The unique ID of the approval request.

Arguments string

A JSON string of arguments for the tool.

Name string

The name of the tool to run.

ServerLabel string

The label of the MCP server making the request.

Type McpApprovalRequest

The type of the item. Always mcp_approval_request.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeResponseCreateParamsMaxOutputTokensUnionRespoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Metadata Metadataoptional

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

OutputModalities []stringoptional

The set of modalities the model used to respond, currently the only possible values are [\"audio\"], [\"text\"]. Audio output always include a text transcript. Setting the output to mode text will disable audio output from the model.

Accepts one of the following:
const RealtimeResponseCreateParamsOutputModalityText RealtimeResponseCreateParamsOutputModality = "text"
const RealtimeResponseCreateParamsOutputModalityAudio RealtimeResponseCreateParamsOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

ToolChoice RealtimeResponseCreateParamsToolChoiceUnionRespoptional

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Accepts one of the following:
type ToolChoiceOptions string

Controls which (if any) tool is called by the model.

none means the model will not call any tool and instead generates a message.

auto means the model can pick between generating a message or calling one or more tools.

required means the model must call one or more tools.

Accepts one of the following:
const ToolChoiceOptionsNone ToolChoiceOptions = "none"
const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
type ToolChoiceFunction struct{…}

Use this option to force the model to call a specific function.

Name string

The name of the function to call.

Type Function

For function calling, the type is always function.

type ToolChoiceMcp struct{…}

Use this option to force the model to call a specific tool on a remote MCP server.

ServerLabel string

The label of the MCP server to use.

Type Mcp

For MCP tools, the type is always mcp.

Name stringoptional

The name of the tool to call on the server.

Tools []RealtimeResponseCreateParamsToolUnionRespoptional

Tools available to the model.

Accepts one of the following:
type RealtimeFunctionTool struct{…}
Description stringoptional

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

Name stringoptional

The name of the function.

Parameters anyoptional

Parameters of the function in JSON Schema.

Type RealtimeFunctionToolTypeoptional

The type of the tool, i.e. function.

type RealtimeResponseCreateMcpTool struct{…}

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

ServerLabel string

A label for this MCP server, used to identify it in tool calls.

Type Mcp

The type of the MCP tool. Always mcp.

AllowedTools RealtimeResponseCreateMcpToolAllowedToolsUnionoptional

List of allowed tool names or a filter object.

Accepts one of the following:
[]string
RealtimeResponseCreateMcpToolAllowedToolsMcpToolFilter
ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Authorization stringoptional

An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.

ConnectorID RealtimeResponseCreateMcpToolConnectorIDoptional

Identifier for service connectors, like those available in ChatGPT. One of server_url or connector_id must be provided. Learn more about service connectors here.

Currently supported connector_id values are:

  • Dropbox: connector_dropbox
  • Gmail: connector_gmail
  • Google Calendar: connector_googlecalendar
  • Google Drive: connector_googledrive
  • Microsoft Teams: connector_microsoftteams
  • Outlook Calendar: connector_outlookcalendar
  • Outlook Email: connector_outlookemail
  • SharePoint: connector_sharepoint
Accepts one of the following:
const RealtimeResponseCreateMcpToolConnectorIDConnectorDropbox RealtimeResponseCreateMcpToolConnectorID = "connector_dropbox"
const RealtimeResponseCreateMcpToolConnectorIDConnectorGmail RealtimeResponseCreateMcpToolConnectorID = "connector_gmail"
const RealtimeResponseCreateMcpToolConnectorIDConnectorGooglecalendar RealtimeResponseCreateMcpToolConnectorID = "connector_googlecalendar"
const RealtimeResponseCreateMcpToolConnectorIDConnectorGoogledrive RealtimeResponseCreateMcpToolConnectorID = "connector_googledrive"
const RealtimeResponseCreateMcpToolConnectorIDConnectorMicrosoftteams RealtimeResponseCreateMcpToolConnectorID = "connector_microsoftteams"
const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookcalendar RealtimeResponseCreateMcpToolConnectorID = "connector_outlookcalendar"
const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookemail RealtimeResponseCreateMcpToolConnectorID = "connector_outlookemail"
const RealtimeResponseCreateMcpToolConnectorIDConnectorSharepoint RealtimeResponseCreateMcpToolConnectorID = "connector_sharepoint"
Headers map[string, string]optional

Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.

RequireApproval RealtimeResponseCreateMcpToolRequireApprovalUnionoptional

Specify which of the MCP server's tools require approval.

Accepts one of the following:
RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilter
Always RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterAlwaysoptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Never RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterNeveroptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

string
Accepts one of the following:
const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "always"
const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "never"
ServerDescription stringoptional

Optional description of the MCP server, used to provide more context.

ServerURL stringoptional

The URL for the MCP server. One of server_url or connector_id must be provided.

type RealtimeResponseStatus struct{…}

Additional details about the status.

Error RealtimeResponseStatusErroroptional

A description of the error that caused the response to fail, populated when the status is failed.

Code stringoptional

Error code, if any.

Type stringoptional

The type of error.

Reason RealtimeResponseStatusReasonoptional

The reason the Response did not complete. For a cancelled Response, one of turn_detected (the server VAD detected a new start of speech) or client_cancelled (the client sent a cancel event). For an incomplete Response, one of max_output_tokens or content_filter (the server-side safety filter activated and cut off the response).

Accepts one of the following:
const RealtimeResponseStatusReasonTurnDetected RealtimeResponseStatusReason = "turn_detected"
const RealtimeResponseStatusReasonClientCancelled RealtimeResponseStatusReason = "client_cancelled"
const RealtimeResponseStatusReasonMaxOutputTokens RealtimeResponseStatusReason = "max_output_tokens"
const RealtimeResponseStatusReasonContentFilter RealtimeResponseStatusReason = "content_filter"
Type RealtimeResponseStatusTypeoptional

The type of error that caused the response to fail, corresponding with the status field (completed, cancelled, incomplete, failed).

Accepts one of the following:
const RealtimeResponseStatusTypeCompleted RealtimeResponseStatusType = "completed"
const RealtimeResponseStatusTypeCancelled RealtimeResponseStatusType = "cancelled"
const RealtimeResponseStatusTypeIncomplete RealtimeResponseStatusType = "incomplete"
const RealtimeResponseStatusTypeFailed RealtimeResponseStatusType = "failed"
type RealtimeResponseUsage struct{…}

Usage statistics for the Response, this will correspond to billing. A Realtime API session will maintain a conversation context and append new Items to the Conversation, thus output from previous turns (text and audio tokens) will become the input for later turns.

InputTokenDetails RealtimeResponseUsageInputTokenDetailsoptional

Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens.

InputTokens int64optional

The number of input tokens used in the Response, including text and audio tokens.

OutputTokenDetails RealtimeResponseUsageOutputTokenDetailsoptional

Details about the output tokens used in the Response.

OutputTokens int64optional

The number of output tokens sent in the Response, including text and audio tokens.

TotalTokens int64optional

The total number of tokens in the Response including input and output text and audio tokens.

type RealtimeResponseUsageInputTokenDetails struct{…}

Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens.

AudioTokens int64optional

The number of audio tokens used as input for the Response.

CachedTokens int64optional

The number of cached tokens used as input for the Response.

CachedTokensDetails RealtimeResponseUsageInputTokenDetailsCachedTokensDetailsoptional

Details about the cached tokens used as input for the Response.

AudioTokens int64optional

The number of cached audio tokens used as input for the Response.

ImageTokens int64optional

The number of cached image tokens used as input for the Response.

TextTokens int64optional

The number of cached text tokens used as input for the Response.

ImageTokens int64optional

The number of image tokens used as input for the Response.

TextTokens int64optional

The number of text tokens used as input for the Response.

type RealtimeResponseUsageOutputTokenDetails struct{…}

Details about the output tokens used in the Response.

AudioTokens int64optional

The number of audio tokens used in the Response.

TextTokens int64optional

The number of text tokens used in the Response.

type RealtimeServerEventUnion interface{…}

A realtime server event.

Accepts one of the following:
type ConversationCreatedEvent struct{…}

Returned when a conversation is created. Emitted right after session creation.

Conversation ConversationCreatedEventConversation

The conversation resource.

ID stringoptional

The unique ID of the conversation.

Object stringoptional

The object type, must be realtime.conversation.

EventID string

The unique ID of the server event.

Type ConversationCreated

The event type, must be conversation.created.

type ConversationItemCreatedEvent struct{…}

Returned when a conversation item is created. There are several scenarios that produce this event:

  • The server is generating a Response, which if successful will produce either one or two Items, which will be of type message (role assistant) or type function_call.
  • The input audio buffer has been committed, either by the client or the server (in server_vad mode). The server will take the content of the input audio buffer and add it to a new user message Item.
  • The client has sent a conversation.item.create event to add a new Item to the Conversation.
EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

Type ConversationItemCreated

The event type, must be conversation.item.created.

PreviousItemID stringoptional

The ID of the preceding item in the Conversation context, allows the client to understand the order of the conversation. Can be null if the item has no predecessor.

type ConversationItemDeletedEvent struct{…}

Returned when an item in the conversation is deleted by the client with a conversation.item.delete event. This event is used to synchronize the server's understanding of the conversation history with the client's view.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item that was deleted.

Type ConversationItemDeleted

The event type, must be conversation.item.deleted.

type ConversationItemInputAudioTranscriptionCompletedEvent struct{…}

This event is the output of audio transcription for user audio written to the user audio buffer. Transcription begins when the input audio buffer is committed by the client or server (when VAD is enabled). Transcription runs asynchronously with Response creation, so this event may come before or after the Response events.

Realtime API models accept audio natively, and thus input transcription is a separate process run on a separate ASR (Automatic Speech Recognition) model. The transcript may diverge somewhat from the model's interpretation, and should be treated as a rough guide.

ContentIndex int64

The index of the content part containing the audio.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item containing the audio that is being transcribed.

Transcript string

The transcribed text.

Type ConversationItemInputAudioTranscriptionCompleted

The event type, must be conversation.item.input_audio_transcription.completed.

Usage ConversationItemInputAudioTranscriptionCompletedEventUsageUnion

Usage statistics for the transcription, this is billed according to the ASR model's pricing rather than the realtime model's pricing.

Accepts one of the following:
ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokens
InputTokens int64

Number of input tokens billed for this request.

OutputTokens int64

Number of output tokens generated.

TotalTokens int64

Total number of tokens used (input + output).

Type Tokens

The type of the usage object. Always tokens for this variant.

InputTokenDetails ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokensInputTokenDetailsoptional

Details about the input tokens billed for this request.

AudioTokens int64optional

Number of audio tokens billed for this request.

TextTokens int64optional

Number of text tokens billed for this request.

ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageDuration
Seconds float64

Duration of the input audio in seconds.

Type Duration

The type of the usage object. Always duration for this variant.

Logprobs []LogProbPropertiesoptional

The log probabilities of the transcription.

Token string

The token that was used to generate the log probability.

Bytes []int64

The bytes that were used to generate the log probability.

Logprob float64

The log probability of the token.

type ConversationItemInputAudioTranscriptionDeltaEvent struct{…}

Returned when the text value of an input audio transcription content part is updated with incremental transcription results.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item containing the audio that is being transcribed.

Type ConversationItemInputAudioTranscriptionDelta

The event type, must be conversation.item.input_audio_transcription.delta.

ContentIndex int64optional

The index of the content part in the item's content array.

Delta stringoptional

The text delta.

Logprobs []LogProbPropertiesoptional

The log probabilities of the transcription. These can be enabled by configurating the session with "include": ["item.input_audio_transcription.logprobs"]. Each entry in the array corresponds a log probability of which token would be selected for this chunk of transcription. This can help to identify if it was possible there were multiple valid options for a given chunk of transcription.

Token string

The token that was used to generate the log probability.

Bytes []int64

The bytes that were used to generate the log probability.

Logprob float64

The log probability of the token.

type ConversationItemInputAudioTranscriptionFailedEvent struct{…}

Returned when input audio transcription is configured, and a transcription request for a user message failed. These events are separate from other error events so that the client can identify the related Item.

ContentIndex int64

The index of the content part containing the audio.

Error ConversationItemInputAudioTranscriptionFailedEventError

Details of the transcription error.

Code stringoptional

Error code, if any.

Message stringoptional

A human-readable error message.

Param stringoptional

Parameter related to the error, if any.

Type stringoptional

The type of error.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item.

Type ConversationItemInputAudioTranscriptionFailed

The event type, must be conversation.item.input_audio_transcription.failed.

RealtimeServerEventConversationItemRetrieved
EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

Type ConversationItemRetrieved

The event type, must be conversation.item.retrieved.

type ConversationItemTruncatedEvent struct{…}

Returned when an earlier assistant audio message item is truncated by the client with a conversation.item.truncate event. This event is used to synchronize the server's understanding of the audio with the client's playback.

This action will truncate the audio and remove the server-side text transcript to ensure there is no text in the context that hasn't been heard by the user.

AudioEndMs int64

The duration up to which the audio was truncated, in milliseconds.

ContentIndex int64

The index of the content part that was truncated.

EventID string

The unique ID of the server event.

ItemID string

The ID of the assistant message item that was truncated.

Type ConversationItemTruncated

The event type, must be conversation.item.truncated.

type RealtimeErrorEvent struct{…}

Returned when an error occurs, which could be a client problem or a server problem. Most errors are recoverable and the session will stay open, we recommend to implementors to monitor and log error messages by default.

Details of the error.

EventID string

The unique ID of the server event.

Type Error

The event type, must be error.

type InputAudioBufferClearedEvent struct{…}

Returned when the input audio buffer is cleared by the client with a input_audio_buffer.clear event.

EventID string

The unique ID of the server event.

Type InputAudioBufferCleared

The event type, must be input_audio_buffer.cleared.

type InputAudioBufferCommittedEvent struct{…}

Returned when an input audio buffer is committed, either by the client or automatically in server VAD mode. The item_id property is the ID of the user message item that will be created, thus a conversation.item.created event will also be sent to the client.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item that will be created.

Type InputAudioBufferCommitted

The event type, must be input_audio_buffer.committed.

PreviousItemID stringoptional

The ID of the preceding item after which the new item will be inserted. Can be null if the item has no predecessor.

type InputAudioBufferDtmfEventReceivedEvent struct{…}

SIP Only: Returned when an DTMF event is received. A DTMF event is a message that represents a telephone keypad press (0–9, *, #, A–D). The event property is the keypad that the user press. The received_at is the UTC Unix Timestamp that the server received the event.

Event string

The telephone keypad that was pressed by the user.

ReceivedAt int64

UTC Unix Timestamp when DTMF Event was received by server.

Type InputAudioBufferDtmfEventReceived

The event type, must be input_audio_buffer.dtmf_event_received.

type InputAudioBufferSpeechStartedEvent struct{…}

Sent by the server when in server_vad mode to indicate that speech has been detected in the audio buffer. This can happen any time audio is added to the buffer (unless speech is already detected). The client may want to use this event to interrupt audio playback or provide visual feedback to the user.

The client should expect to receive a input_audio_buffer.speech_stopped event when speech stops. The item_id property is the ID of the user message item that will be created when speech stops and will also be included in the input_audio_buffer.speech_stopped event (unless the client manually commits the audio buffer during VAD activation).

AudioStartMs int64

Milliseconds from the start of all audio written to the buffer during the session when speech was first detected. This will correspond to the beginning of audio sent to the model, and thus includes the prefix_padding_ms configured in the Session.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item that will be created when speech stops.

Type InputAudioBufferSpeechStarted

The event type, must be input_audio_buffer.speech_started.

type InputAudioBufferSpeechStoppedEvent struct{…}

Returned in server_vad mode when the server detects the end of speech in the audio buffer. The server will also send an conversation.item.created event with the user message item that is created from the audio buffer.

AudioEndMs int64

Milliseconds since the session started when speech stopped. This will correspond to the end of audio sent to the model, and thus includes the min_silence_duration_ms configured in the Session.

EventID string

The unique ID of the server event.

ItemID string

The ID of the user message item that will be created.

Type InputAudioBufferSpeechStopped

The event type, must be input_audio_buffer.speech_stopped.

type RateLimitsUpdatedEvent struct{…}

Emitted at the beginning of a Response to indicate the updated rate limits. When a Response is created some tokens will be "reserved" for the output tokens, the rate limits shown here reflect that reservation, which is then adjusted accordingly once the Response is completed.

EventID string

The unique ID of the server event.

RateLimits []RateLimitsUpdatedEventRateLimit

List of rate limit information.

Limit int64optional

The maximum allowed value for the rate limit.

Name stringoptional

The name of the rate limit (requests, tokens).

Accepts one of the following:
const RateLimitsUpdatedEventRateLimitNameRequests RateLimitsUpdatedEventRateLimitName = "requests"
const RateLimitsUpdatedEventRateLimitNameTokens RateLimitsUpdatedEventRateLimitName = "tokens"
Remaining int64optional

The remaining value before the limit is reached.

ResetSeconds float64optional

Seconds until the rate limit resets.

Type RateLimitsUpdated

The event type, must be rate_limits.updated.

type ResponseAudioDeltaEvent struct{…}

Returned when the model-generated audio is updated.

ContentIndex int64

The index of the content part in the item's content array.

Delta string

Base64-encoded audio data delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputAudioDelta

The event type, must be response.output_audio.delta.

type ResponseAudioDoneEvent struct{…}

Returned when the model-generated audio is done. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputAudioDone

The event type, must be response.output_audio.done.

type ResponseAudioTranscriptDeltaEvent struct{…}

Returned when the model-generated transcription of audio output is updated.

ContentIndex int64

The index of the content part in the item's content array.

Delta string

The transcript delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputAudioTranscriptDelta

The event type, must be response.output_audio_transcript.delta.

type ResponseAudioTranscriptDoneEvent struct{…}

Returned when the model-generated transcription of audio output is done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Transcript string

The final transcript of the audio.

Type ResponseOutputAudioTranscriptDone

The event type, must be response.output_audio_transcript.done.

type ResponseContentPartAddedEvent struct{…}

Returned when a new content part is added to an assistant message item during response generation.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item to which the content part was added.

OutputIndex int64

The index of the output item in the response.

Part ResponseContentPartAddedEventPart

The content part that was added.

Audio stringoptional

Base64-encoded audio data (if type is "audio").

Text stringoptional

The text content (if type is "text").

Transcript stringoptional

The transcript of the audio (if type is "audio").

Type stringoptional

The content type ("text", "audio").

Accepts one of the following:
const ResponseContentPartAddedEventPartTypeText ResponseContentPartAddedEventPartType = "text"
const ResponseContentPartAddedEventPartTypeAudio ResponseContentPartAddedEventPartType = "audio"
ResponseID string

The ID of the response.

Type ResponseContentPartAdded

The event type, must be response.content_part.added.

type ResponseContentPartDoneEvent struct{…}

Returned when a content part is done streaming in an assistant message item. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

Part ResponseContentPartDoneEventPart

The content part that is done.

Audio stringoptional

Base64-encoded audio data (if type is "audio").

Text stringoptional

The text content (if type is "text").

Transcript stringoptional

The transcript of the audio (if type is "audio").

Type stringoptional

The content type ("text", "audio").

Accepts one of the following:
const ResponseContentPartDoneEventPartTypeText ResponseContentPartDoneEventPartType = "text"
const ResponseContentPartDoneEventPartTypeAudio ResponseContentPartDoneEventPartType = "audio"
ResponseID string

The ID of the response.

Type ResponseContentPartDone

The event type, must be response.content_part.done.

type ResponseCreatedEvent struct{…}

Returned when a new Response is created. The first event of response creation, where the response is in an initial state of in_progress.

EventID string

The unique ID of the server event.

The response resource.

Type ResponseCreated

The event type, must be response.created.

type ResponseDoneEvent struct{…}

Returned when a Response is done streaming. Always emitted, no matter the final state. The Response object included in the response.done event will include all output Items in the Response but will omit the raw audio data.

Clients should check the status field of the Response to determine if it was successful (completed) or if there was another outcome: cancelled, failed, or incomplete.

A response will contain all output items that were generated during the response, excluding any audio content.

EventID string

The unique ID of the server event.

The response resource.

Type ResponseDone

The event type, must be response.done.

type ResponseFunctionCallArgumentsDeltaEvent struct{…}

Returned when the model-generated function call arguments are updated.

CallID string

The ID of the function call.

Delta string

The arguments delta as a JSON string.

EventID string

The unique ID of the server event.

ItemID string

The ID of the function call item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseFunctionCallArgumentsDelta

The event type, must be response.function_call_arguments.delta.

type ResponseFunctionCallArgumentsDoneEvent struct{…}

Returned when the model-generated function call arguments are done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

Arguments string

The final arguments as a JSON string.

CallID string

The ID of the function call.

EventID string

The unique ID of the server event.

ItemID string

The ID of the function call item.

Name string

The name of the function that was called.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseFunctionCallArgumentsDone

The event type, must be response.function_call_arguments.done.

type ResponseOutputItemAddedEvent struct{…}

Returned when a new Item is created during Response generation.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

OutputIndex int64

The index of the output item in the Response.

ResponseID string

The ID of the Response to which the item belongs.

Type ResponseOutputItemAdded

The event type, must be response.output_item.added.

type ResponseOutputItemDoneEvent struct{…}

Returned when an Item is done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

OutputIndex int64

The index of the output item in the Response.

ResponseID string

The ID of the Response to which the item belongs.

Type ResponseOutputItemDone

The event type, must be response.output_item.done.

type ResponseTextDeltaEvent struct{…}

Returned when the text value of an "output_text" content part is updated.

ContentIndex int64

The index of the content part in the item's content array.

Delta string

The text delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputTextDelta

The event type, must be response.output_text.delta.

type ResponseTextDoneEvent struct{…}

Returned when the text value of an "output_text" content part is done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Text string

The final text content.

Type ResponseOutputTextDone

The event type, must be response.output_text.done.

type SessionCreatedEvent struct{…}

Returned when a Session is created. Emitted automatically when a new connection is established as the first server event. This event will contain the default Session configuration.

EventID string

The unique ID of the server event.

Session SessionCreatedEventSessionUnion

The session configuration.

Accepts one of the following:
type RealtimeSessionCreateRequest struct{…}

Realtime session object configuration.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeAudioConfigoptional

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Model RealtimeSessionCreateRequestModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionCreateRequestModel
Accepts one of the following:
const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"
const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"
const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Tools RealtimeToolsConfigoptional

Tools available to the model.

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeTranscriptionSessionCreateRequest struct{…}

Realtime transcription session object configuration.

Type Transcription

The type of session to create. Always transcription for transcription sessions.

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Type SessionCreated

The event type, must be session.created.

type SessionUpdatedEvent struct{…}

Returned when a session is updated with a session.update event, unless there is an error.

EventID string

The unique ID of the server event.

Session SessionUpdatedEventSessionUnion

The session configuration.

Accepts one of the following:
type RealtimeSessionCreateRequest struct{…}

Realtime session object configuration.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeAudioConfigoptional

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Model RealtimeSessionCreateRequestModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionCreateRequestModel
Accepts one of the following:
const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"
const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"
const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Tools RealtimeToolsConfigoptional

Tools available to the model.

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeTranscriptionSessionCreateRequest struct{…}

Realtime transcription session object configuration.

Type Transcription

The type of session to create. Always transcription for transcription sessions.

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Type SessionUpdated

The event type, must be session.updated.

RealtimeServerEventOutputAudioBufferStarted
EventID string

The unique ID of the server event.

ResponseID string

The unique ID of the response that produced the audio.

Type OutputAudioBufferStarted

The event type, must be output_audio_buffer.started.

RealtimeServerEventOutputAudioBufferStopped
EventID string

The unique ID of the server event.

ResponseID string

The unique ID of the response that produced the audio.

Type OutputAudioBufferStopped

The event type, must be output_audio_buffer.stopped.

RealtimeServerEventOutputAudioBufferCleared
EventID string

The unique ID of the server event.

ResponseID string

The unique ID of the response that produced the audio.

Type OutputAudioBufferCleared

The event type, must be output_audio_buffer.cleared.

type ConversationItemAdded struct{…}

Sent by the server when an Item is added to the default Conversation. This can happen in several cases:

  • When the client sends a conversation.item.create event.
  • When the input audio buffer is committed. In this case the item will be a user message containing the audio from the buffer.
  • When the model is generating a Response. In this case the conversation.item.added event will be sent when the model starts generating a specific Item, and thus it will not yet have any content (and status will be in_progress).

The event will include the full content of the Item (except when model is generating a Response) except for audio data, which can be retrieved separately with a conversation.item.retrieve event if necessary.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

Type ConversationItemAdded

The event type, must be conversation.item.added.

PreviousItemID stringoptional

The ID of the item that precedes this one, if any. This is used to maintain ordering when items are inserted.

type ConversationItemDone struct{…}

Returned when a conversation item is finalized.

The event will include the full content of the Item except for audio data, which can be retrieved separately with a conversation.item.retrieve event if needed.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

Type ConversationItemDone

The event type, must be conversation.item.done.

PreviousItemID stringoptional

The ID of the item that precedes this one, if any. This is used to maintain ordering when items are inserted.

type InputAudioBufferTimeoutTriggered struct{…}

Returned when the Server VAD timeout is triggered for the input audio buffer. This is configured with idle_timeout_ms in the turn_detection settings of the session, and it indicates that there hasn't been any speech detected for the configured duration.

The audio_start_ms and audio_end_ms fields indicate the segment of audio after the last model response up to the triggering time, as an offset from the beginning of audio written to the input audio buffer. This means it demarcates the segment of audio that was silent and the difference between the start and end values will roughly match the configured timeout.

The empty audio will be committed to the conversation as an input_audio item (there will be a input_audio_buffer.committed event) and a model response will be generated. There may be speech that didn't trigger VAD but is still detected by the model, so the model may respond with something relevant to the conversation or a prompt to continue speaking.

AudioEndMs int64

Millisecond offset of audio written to the input audio buffer at the time the timeout was triggered.

AudioStartMs int64

Millisecond offset of audio written to the input audio buffer that was after the playback time of the last model response.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item associated with this segment.

Type InputAudioBufferTimeoutTriggered

The event type, must be input_audio_buffer.timeout_triggered.

type ConversationItemInputAudioTranscriptionSegment struct{…}

Returned when an input audio transcription segment is identified for an item.

ID string

The segment identifier.

ContentIndex int64

The index of the input audio content part within the item.

End float64

End time of the segment in seconds.

formatfloat
EventID string

The unique ID of the server event.

ItemID string

The ID of the item containing the input audio content.

Speaker string

The detected speaker label for this segment.

Start float64

Start time of the segment in seconds.

formatfloat
Text string

The text for this segment.

Type ConversationItemInputAudioTranscriptionSegment

The event type, must be conversation.item.input_audio_transcription.segment.

type McpListToolsInProgress struct{…}

Returned when listing MCP tools is in progress for an item.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP list tools item.

Type McpListToolsInProgress

The event type, must be mcp_list_tools.in_progress.

type McpListToolsCompleted struct{…}

Returned when listing MCP tools has completed for an item.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP list tools item.

Type McpListToolsCompleted

The event type, must be mcp_list_tools.completed.

type McpListToolsFailed struct{…}

Returned when listing MCP tools has failed for an item.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP list tools item.

Type McpListToolsFailed

The event type, must be mcp_list_tools.failed.

type ResponseMcpCallArgumentsDelta struct{…}

Returned when MCP tool call arguments are updated during response generation.

Delta string

The JSON-encoded arguments delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseMcpCallArgumentsDelta

The event type, must be response.mcp_call_arguments.delta.

Obfuscation stringoptional

If present, indicates the delta text was obfuscated.

type ResponseMcpCallArgumentsDone struct{…}

Returned when MCP tool call arguments are finalized during response generation.

Arguments string

The final JSON-encoded arguments string.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseMcpCallArgumentsDone

The event type, must be response.mcp_call_arguments.done.

type ResponseMcpCallInProgress struct{…}

Returned when an MCP tool call has started and is in progress.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

Type ResponseMcpCallInProgress

The event type, must be response.mcp_call.in_progress.

type ResponseMcpCallCompleted struct{…}

Returned when an MCP tool call has completed successfully.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

Type ResponseMcpCallCompleted

The event type, must be response.mcp_call.completed.

type ResponseMcpCallFailed struct{…}

Returned when an MCP tool call has failed.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

Type ResponseMcpCallFailed

The event type, must be response.mcp_call.failed.

type RealtimeSession struct{…}

Realtime session object for the beta interface.

ID stringoptional

Unique identifier for the session that looks like sess_1234567890abcdef.

ExpiresAt int64optional

Expiration timestamp for the session, in seconds since epoch.

Include []stringoptional

Additional fields to include in server outputs.

  • item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.
InputAudioFormat RealtimeSessionInputAudioFormatoptional

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

Accepts one of the following:
const RealtimeSessionInputAudioFormatPcm16 RealtimeSessionInputAudioFormat = "pcm16"
const RealtimeSessionInputAudioFormatG711Ulaw RealtimeSessionInputAudioFormat = "g711_ulaw"
const RealtimeSessionInputAudioFormatG711Alaw RealtimeSessionInputAudioFormat = "g711_alaw"
InputAudioNoiseReduction RealtimeSessionInputAudioNoiseReductionoptional

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Type NoiseReductionTypeoptional

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

InputAudioTranscription AudioTranscriptionoptional

Configuration for input audio transcription, defaults to off and can be set to null to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through the /audio/transcriptions endpoint and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxResponseOutputTokens RealtimeSessionMaxResponseOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Modalities []stringoptional

The set of modalities the model can respond with. To disable audio, set this to ["text"].

Accepts one of the following:
const RealtimeSessionModalityText RealtimeSessionModality = "text"
const RealtimeSessionModalityAudio RealtimeSessionModality = "audio"
Model RealtimeSessionModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionModel
Accepts one of the following:
const RealtimeSessionModelGPTRealtime RealtimeSessionModel = "gpt-realtime"
const RealtimeSessionModelGPTRealtime2025_08_28 RealtimeSessionModel = "gpt-realtime-2025-08-28"
const RealtimeSessionModelGPT4oRealtimePreview RealtimeSessionModel = "gpt-4o-realtime-preview"
const RealtimeSessionModelGPT4oRealtimePreview2024_10_01 RealtimeSessionModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionModelGPT4oRealtimePreview2024_12_17 RealtimeSessionModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionModelGPT4oRealtimePreview2025_06_03 RealtimeSessionModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionModelGPT4oMiniRealtimePreview RealtimeSessionModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionModelGPTRealtimeMini RealtimeSessionModel = "gpt-realtime-mini"
const RealtimeSessionModelGPTRealtimeMini2025_10_06 RealtimeSessionModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionModelGPTRealtimeMini2025_12_15 RealtimeSessionModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionModelGPTAudioMini RealtimeSessionModel = "gpt-audio-mini"
const RealtimeSessionModelGPTAudioMini2025_10_06 RealtimeSessionModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionModelGPTAudioMini2025_12_15 RealtimeSessionModel = "gpt-audio-mini-2025-12-15"
Object RealtimeSessionObjectoptional

The object type. Always realtime.session.

OutputAudioFormat RealtimeSessionOutputAudioFormatoptional

The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, output audio is sampled at a rate of 24kHz.

Accepts one of the following:
const RealtimeSessionOutputAudioFormatPcm16 RealtimeSessionOutputAudioFormat = "pcm16"
const RealtimeSessionOutputAudioFormatG711Ulaw RealtimeSessionOutputAudioFormat = "g711_ulaw"
const RealtimeSessionOutputAudioFormatG711Alaw RealtimeSessionOutputAudioFormat = "g711_alaw"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

Speed float64optional

The speed of the model's spoken response. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.

maximum1.5
minimum0.25
Temperature float64optional

Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance.

ToolChoice stringoptional

How the model chooses tools. Options are auto, none, required, or specify a function.

Tools []RealtimeFunctionTooloptional

Tools (functions) available to the model.

Description stringoptional

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

Name stringoptional

The name of the function.

Parameters anyoptional

Parameters of the function in JSON Schema.

Type RealtimeFunctionToolTypeoptional

The type of the tool, i.e. function.

Tracing RealtimeSessionTracingUnionoptional

Configuration options for tracing. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Accepts one of the following:
Auto
RealtimeSessionTracingTracingConfiguration
GroupID stringoptional

The group id to attach to this trace to enable filtering and grouping in the traces dashboard.

Metadata anyoptional

The arbitrary metadata to attach to this trace to enable filtering in the traces dashboard.

WorkflowName stringoptional

The name of the workflow to attach to this trace. This is used to name the trace in the traces dashboard.

TurnDetection RealtimeSessionTurnDetectionUnionoptional

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

Accepts one of the following:
RealtimeSessionTurnDetectionServerVad
Type ServerVad

Type of turn detection, server_vad to turn on simple Server VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs. If interrupt_response is set to false this may fail to create a response if the model is already responding.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

IdleTimeoutMs int64optional

Optional timeout after which a model response will be triggered automatically. This is useful for situations in which a long pause from the user is unexpected, such as a phone call. The model will effectively prompt the user to continue the conversation based on the current context.

The timeout value will be applied after the last model response's audio has finished playing, i.e. it's set to the response.done time plus audio playback duration.

An input_audio_buffer.timeout_triggered event (plus events associated with the Response) will be emitted when the timeout is reached. Idle timeout is currently only supported for server_vad mode.

minimum5000
maximum30000
InterruptResponse booloptional

Whether or not to automatically interrupt (cancel) any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs. If true then the response will be cancelled, otherwise it will continue until complete.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

PrefixPaddingMs int64optional

Used only for server_vad mode. Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

SilenceDurationMs int64optional

Used only for server_vad mode. Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Threshold float64optional

Used only for server_vad mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

RealtimeSessionTurnDetectionSemanticVad
Type SemanticVad

Type of turn detection, semantic_vad to turn on Semantic VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs.

Eagerness stringoptional

Used only for semantic_vad mode. The eagerness of the model to respond. low will wait longer for the user to continue speaking, high will respond more quickly. auto is the default and is equivalent to medium. low, medium, and high have max timeouts of 8s, 4s, and 2s respectively.

Accepts one of the following:
const RealtimeSessionTurnDetectionSemanticVadEagernessLow RealtimeSessionTurnDetectionSemanticVadEagerness = "low"
const RealtimeSessionTurnDetectionSemanticVadEagernessMedium RealtimeSessionTurnDetectionSemanticVadEagerness = "medium"
const RealtimeSessionTurnDetectionSemanticVadEagernessHigh RealtimeSessionTurnDetectionSemanticVadEagerness = "high"
const RealtimeSessionTurnDetectionSemanticVadEagernessAuto RealtimeSessionTurnDetectionSemanticVadEagerness = "auto"
InterruptResponse booloptional

Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs.

Voice RealtimeSessionVoiceoptional

The voice the model uses to respond. Voice cannot be changed during the session once the model has responded with audio at least once. Current voice options are alloy, ash, ballad, coral, echo, sage, shimmer, and verse.

Accepts one of the following:
string
RealtimeSessionVoice
Accepts one of the following:
const RealtimeSessionVoiceAlloy RealtimeSessionVoice = "alloy"
const RealtimeSessionVoiceAsh RealtimeSessionVoice = "ash"
const RealtimeSessionVoiceBallad RealtimeSessionVoice = "ballad"
const RealtimeSessionVoiceCoral RealtimeSessionVoice = "coral"
const RealtimeSessionVoiceEcho RealtimeSessionVoice = "echo"
const RealtimeSessionVoiceSage RealtimeSessionVoice = "sage"
const RealtimeSessionVoiceShimmer RealtimeSessionVoice = "shimmer"
const RealtimeSessionVoiceVerse RealtimeSessionVoice = "verse"
const RealtimeSessionVoiceMarin RealtimeSessionVoice = "marin"
const RealtimeSessionVoiceCedar RealtimeSessionVoice = "cedar"
type RealtimeSessionCreateRequest struct{…}

Realtime session object configuration.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeAudioConfigoptional

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Model RealtimeSessionCreateRequestModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionCreateRequestModel
Accepts one of the following:
const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"
const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"
const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Tools RealtimeToolsConfigoptional

Tools available to the model.

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeToolChoiceConfigUnion interface{…}

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Accepts one of the following:
type ToolChoiceOptions string

Controls which (if any) tool is called by the model.

none means the model will not call any tool and instead generates a message.

auto means the model can pick between generating a message or calling one or more tools.

required means the model must call one or more tools.

Accepts one of the following:
const ToolChoiceOptionsNone ToolChoiceOptions = "none"
const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
type ToolChoiceFunction struct{…}

Use this option to force the model to call a specific function.

Name string

The name of the function to call.

Type Function

For function calling, the type is always function.

type ToolChoiceMcp struct{…}

Use this option to force the model to call a specific tool on a remote MCP server.

ServerLabel string

The label of the MCP server to use.

Type Mcp

For MCP tools, the type is always mcp.

Name stringoptional

The name of the tool to call on the server.

type RealtimeToolsConfig []RealtimeToolsConfigUnion

Tools available to the model.

Accepts one of the following:
type RealtimeFunctionTool struct{…}
Description stringoptional

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

Name stringoptional

The name of the function.

Parameters anyoptional

Parameters of the function in JSON Schema.

Type RealtimeFunctionToolTypeoptional

The type of the tool, i.e. function.

RealtimeToolsConfigUnionMcp
ServerLabel string

A label for this MCP server, used to identify it in tool calls.

Type Mcp

The type of the MCP tool. Always mcp.

AllowedTools RealtimeToolsConfigUnionMcpAllowedToolsoptional

List of allowed tool names or a filter object.

Accepts one of the following:
[]string
RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter
ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Authorization stringoptional

An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.

ConnectorID stringoptional

Identifier for service connectors, like those available in ChatGPT. One of server_url or connector_id must be provided. Learn more about service connectors here.

Currently supported connector_id values are:

  • Dropbox: connector_dropbox
  • Gmail: connector_gmail
  • Google Calendar: connector_googlecalendar
  • Google Drive: connector_googledrive
  • Microsoft Teams: connector_microsoftteams
  • Outlook Calendar: connector_outlookcalendar
  • Outlook Email: connector_outlookemail
  • SharePoint: connector_sharepoint
Accepts one of the following:
const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"
Headers map[string, string]optional

Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.

RequireApproval RealtimeToolsConfigUnionMcpRequireApprovaloptional

Specify which of the MCP server's tools require approval.

Accepts one of the following:
RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter
Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlwaysoptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNeveroptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

string
Accepts one of the following:
const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"
const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"
ServerDescription stringoptional

Optional description of the MCP server, used to provide more context.

ServerURL stringoptional

The URL for the MCP server. One of server_url or connector_id must be provided.

type RealtimeToolsConfigUnion interface{…}

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

Accepts one of the following:
type RealtimeFunctionTool struct{…}
Description stringoptional

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

Name stringoptional

The name of the function.

Parameters anyoptional

Parameters of the function in JSON Schema.

Type RealtimeFunctionToolTypeoptional

The type of the tool, i.e. function.

RealtimeToolsConfigUnionMcp
ServerLabel string

A label for this MCP server, used to identify it in tool calls.

Type Mcp

The type of the MCP tool. Always mcp.

AllowedTools RealtimeToolsConfigUnionMcpAllowedToolsoptional

List of allowed tool names or a filter object.

Accepts one of the following:
[]string
RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter
ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Authorization stringoptional

An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.

ConnectorID stringoptional

Identifier for service connectors, like those available in ChatGPT. One of server_url or connector_id must be provided. Learn more about service connectors here.

Currently supported connector_id values are:

  • Dropbox: connector_dropbox
  • Gmail: connector_gmail
  • Google Calendar: connector_googlecalendar
  • Google Drive: connector_googledrive
  • Microsoft Teams: connector_microsoftteams
  • Outlook Calendar: connector_outlookcalendar
  • Outlook Email: connector_outlookemail
  • SharePoint: connector_sharepoint
Accepts one of the following:
const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"
const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"
Headers map[string, string]optional

Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.

RequireApproval RealtimeToolsConfigUnionMcpRequireApprovaloptional

Specify which of the MCP server's tools require approval.

Accepts one of the following:
RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter
Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlwaysoptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNeveroptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

string
Accepts one of the following:
const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"
const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"
ServerDescription stringoptional

Optional description of the MCP server, used to provide more context.

ServerURL stringoptional

The URL for the MCP server. One of server_url or connector_id must be provided.

type RealtimeTracingConfigUnion interface{…}

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Accepts one of the following:
Auto
RealtimeTracingConfigTracingConfiguration
GroupID stringoptional

The group id to attach to this trace to enable filtering and grouping in the Traces Dashboard.

Metadata anyoptional

The arbitrary metadata to attach to this trace to enable filtering in the Traces Dashboard.

WorkflowName stringoptional

The name of the workflow to attach to this trace. This is used to name the trace in the Traces Dashboard.

type RealtimeTranscriptionSessionAudio struct{…}

Configuration for input and output audio.

type RealtimeTranscriptionSessionAudioInput struct{…}

The PCM audio format. Only a 24kHz sample rate is supported.

NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReductionoptional

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Type NoiseReductionTypeoptional

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

Transcription AudioTranscriptionoptional

Configuration for input audio transcription, defaults to off and can be set to null to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through the /audio/transcriptions endpoint and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

type RealtimeTranscriptionSessionAudioInputTurnDetectionUnion interface{…}

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

Accepts one of the following:
RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad
Type ServerVad

Type of turn detection, server_vad to turn on simple Server VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs. If interrupt_response is set to false this may fail to create a response if the model is already responding.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

IdleTimeoutMs int64optional

Optional timeout after which a model response will be triggered automatically. This is useful for situations in which a long pause from the user is unexpected, such as a phone call. The model will effectively prompt the user to continue the conversation based on the current context.

The timeout value will be applied after the last model response's audio has finished playing, i.e. it's set to the response.done time plus audio playback duration.

An input_audio_buffer.timeout_triggered event (plus events associated with the Response) will be emitted when the timeout is reached. Idle timeout is currently only supported for server_vad mode.

minimum5000
maximum30000
InterruptResponse booloptional

Whether or not to automatically interrupt (cancel) any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs. If true then the response will be cancelled, otherwise it will continue until complete.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

PrefixPaddingMs int64optional

Used only for server_vad mode. Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

SilenceDurationMs int64optional

Used only for server_vad mode. Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Threshold float64optional

Used only for server_vad mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad
Type SemanticVad

Type of turn detection, semantic_vad to turn on Semantic VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs.

Eagerness stringoptional

Used only for semantic_vad mode. The eagerness of the model to respond. low will wait longer for the user to continue speaking, high will respond more quickly. auto is the default and is equivalent to medium. low, medium, and high have max timeouts of 8s, 4s, and 2s respectively.

Accepts one of the following:
const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"
const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"
const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"
const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"
InterruptResponse booloptional

Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs.

type RealtimeTranscriptionSessionCreateRequest struct{…}

Realtime transcription session object configuration.

Type Transcription

The type of session to create. Always transcription for transcription sessions.

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

type RealtimeTruncationUnion interface{…}

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

Accepts one of the following:
type RealtimeTruncationRealtimeTruncationStrategy string

The truncation strategy to use for the session. auto is the default truncation strategy. disabled will disable truncation and emit errors when the conversation exceeds the input token limit.

Accepts one of the following:
const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"
const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"
type RealtimeTruncationRetentionRatio struct{…}

Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage.

RetentionRatio float64

Fraction of post-instruction conversation tokens to retain (0.0 - 1.0) when the conversation exceeds the input token limit. Setting this to 0.8 means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates.

minimum0
maximum1
Type RetentionRatio

Use retention ratio truncation.

TokenLimits RealtimeTruncationRetentionRatioTokenLimitsoptional

Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used.

PostInstructions int64optional

Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens.

minimum0
type RealtimeTruncationRetentionRatio struct{…}

Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage.

RetentionRatio float64

Fraction of post-instruction conversation tokens to retain (0.0 - 1.0) when the conversation exceeds the input token limit. Setting this to 0.8 means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates.

minimum0
maximum1
Type RetentionRatio

Use retention ratio truncation.

TokenLimits RealtimeTruncationRetentionRatioTokenLimitsoptional

Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used.

PostInstructions int64optional

Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens.

minimum0
type ResponseAudioDeltaEvent struct{…}

Returned when the model-generated audio is updated.

ContentIndex int64

The index of the content part in the item's content array.

Delta string

Base64-encoded audio data delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputAudioDelta

The event type, must be response.output_audio.delta.

type ResponseAudioDoneEvent struct{…}

Returned when the model-generated audio is done. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputAudioDone

The event type, must be response.output_audio.done.

type ResponseAudioTranscriptDeltaEvent struct{…}

Returned when the model-generated transcription of audio output is updated.

ContentIndex int64

The index of the content part in the item's content array.

Delta string

The transcript delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputAudioTranscriptDelta

The event type, must be response.output_audio_transcript.delta.

type ResponseAudioTranscriptDoneEvent struct{…}

Returned when the model-generated transcription of audio output is done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Transcript string

The final transcript of the audio.

Type ResponseOutputAudioTranscriptDone

The event type, must be response.output_audio_transcript.done.

type ResponseCancelEvent struct{…}

Send this event to cancel an in-progress response. The server will respond with a response.done event with a status of response.status=cancelled. If there is no response to cancel, the server will respond with an error. It's safe to call response.cancel even if no response is in progress, an error will be returned the session will remain unaffected.

Type ResponseCancel

The event type, must be response.cancel.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512
ResponseID stringoptional

A specific response ID to cancel - if not provided, will cancel an in-progress response in the default conversation.

type ResponseContentPartAddedEvent struct{…}

Returned when a new content part is added to an assistant message item during response generation.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item to which the content part was added.

OutputIndex int64

The index of the output item in the response.

Part ResponseContentPartAddedEventPart

The content part that was added.

Audio stringoptional

Base64-encoded audio data (if type is "audio").

Text stringoptional

The text content (if type is "text").

Transcript stringoptional

The transcript of the audio (if type is "audio").

Type stringoptional

The content type ("text", "audio").

Accepts one of the following:
const ResponseContentPartAddedEventPartTypeText ResponseContentPartAddedEventPartType = "text"
const ResponseContentPartAddedEventPartTypeAudio ResponseContentPartAddedEventPartType = "audio"
ResponseID string

The ID of the response.

Type ResponseContentPartAdded

The event type, must be response.content_part.added.

type ResponseContentPartDoneEvent struct{…}

Returned when a content part is done streaming in an assistant message item. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

Part ResponseContentPartDoneEventPart

The content part that is done.

Audio stringoptional

Base64-encoded audio data (if type is "audio").

Text stringoptional

The text content (if type is "text").

Transcript stringoptional

The transcript of the audio (if type is "audio").

Type stringoptional

The content type ("text", "audio").

Accepts one of the following:
const ResponseContentPartDoneEventPartTypeText ResponseContentPartDoneEventPartType = "text"
const ResponseContentPartDoneEventPartTypeAudio ResponseContentPartDoneEventPartType = "audio"
ResponseID string

The ID of the response.

Type ResponseContentPartDone

The event type, must be response.content_part.done.

type ResponseCreateEvent struct{…}

This event instructs the server to create a Response, which means triggering model inference. When in Server VAD mode, the server will create Responses automatically.

A Response will include at least one Item, and may have two, in which case the second will be a function call. These Items will be appended to the conversation history by default.

The server will respond with a response.created event, events for Items and content created, and finally a response.done event to indicate the Response is complete.

The response.create event includes inference configuration like instructions and tools. If these are set, they will override the Session's configuration for this Response only.

Responses can be created out-of-band of the default Conversation, meaning that they can have arbitrary input, and it's possible to disable writing the output to the Conversation. Only one Response can write to the default Conversation at a time, but otherwise multiple Responses can be created in parallel. The metadata field is a good way to disambiguate multiple simultaneous Responses.

Clients can set conversation to none to create a Response that does not write to the default Conversation. Arbitrary input can be provided with the input field, which is an array accepting raw Items and references to existing Items.

Type ResponseCreate

The event type, must be response.create.

EventID stringoptional

Optional client-generated ID used to identify this event.

maxLength512

Create a new Realtime response with these parameters

type ResponseCreatedEvent struct{…}

Returned when a new Response is created. The first event of response creation, where the response is in an initial state of in_progress.

EventID string

The unique ID of the server event.

The response resource.

Type ResponseCreated

The event type, must be response.created.

type ResponseDoneEvent struct{…}

Returned when a Response is done streaming. Always emitted, no matter the final state. The Response object included in the response.done event will include all output Items in the Response but will omit the raw audio data.

Clients should check the status field of the Response to determine if it was successful (completed) or if there was another outcome: cancelled, failed, or incomplete.

A response will contain all output items that were generated during the response, excluding any audio content.

EventID string

The unique ID of the server event.

The response resource.

Type ResponseDone

The event type, must be response.done.

type ResponseFunctionCallArgumentsDeltaEvent struct{…}

Returned when the model-generated function call arguments are updated.

CallID string

The ID of the function call.

Delta string

The arguments delta as a JSON string.

EventID string

The unique ID of the server event.

ItemID string

The ID of the function call item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseFunctionCallArgumentsDelta

The event type, must be response.function_call_arguments.delta.

type ResponseFunctionCallArgumentsDoneEvent struct{…}

Returned when the model-generated function call arguments are done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

Arguments string

The final arguments as a JSON string.

CallID string

The ID of the function call.

EventID string

The unique ID of the server event.

ItemID string

The ID of the function call item.

Name string

The name of the function that was called.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseFunctionCallArgumentsDone

The event type, must be response.function_call_arguments.done.

type ResponseMcpCallArgumentsDelta struct{…}

Returned when MCP tool call arguments are updated during response generation.

Delta string

The JSON-encoded arguments delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseMcpCallArgumentsDelta

The event type, must be response.mcp_call_arguments.delta.

Obfuscation stringoptional

If present, indicates the delta text was obfuscated.

type ResponseMcpCallArgumentsDone struct{…}

Returned when MCP tool call arguments are finalized during response generation.

Arguments string

The final JSON-encoded arguments string.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseMcpCallArgumentsDone

The event type, must be response.mcp_call_arguments.done.

type ResponseMcpCallCompleted struct{…}

Returned when an MCP tool call has completed successfully.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

Type ResponseMcpCallCompleted

The event type, must be response.mcp_call.completed.

type ResponseMcpCallFailed struct{…}

Returned when an MCP tool call has failed.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

Type ResponseMcpCallFailed

The event type, must be response.mcp_call.failed.

type ResponseMcpCallInProgress struct{…}

Returned when an MCP tool call has started and is in progress.

EventID string

The unique ID of the server event.

ItemID string

The ID of the MCP tool call item.

OutputIndex int64

The index of the output item in the response.

Type ResponseMcpCallInProgress

The event type, must be response.mcp_call.in_progress.

type ResponseOutputItemAddedEvent struct{…}

Returned when a new Item is created during Response generation.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

OutputIndex int64

The index of the output item in the Response.

ResponseID string

The ID of the Response to which the item belongs.

Type ResponseOutputItemAdded

The event type, must be response.output_item.added.

type ResponseOutputItemDoneEvent struct{…}

Returned when an Item is done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

EventID string

The unique ID of the server event.

A single item within a Realtime conversation.

OutputIndex int64

The index of the output item in the Response.

ResponseID string

The ID of the Response to which the item belongs.

Type ResponseOutputItemDone

The event type, must be response.output_item.done.

type ResponseTextDeltaEvent struct{…}

Returned when the text value of an "output_text" content part is updated.

ContentIndex int64

The index of the content part in the item's content array.

Delta string

The text delta.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Type ResponseOutputTextDelta

The event type, must be response.output_text.delta.

type ResponseTextDoneEvent struct{…}

Returned when the text value of an "output_text" content part is done streaming. Also emitted when a Response is interrupted, incomplete, or cancelled.

ContentIndex int64

The index of the content part in the item's content array.

EventID string

The unique ID of the server event.

ItemID string

The ID of the item.

OutputIndex int64

The index of the output item in the response.

ResponseID string

The ID of the response.

Text string

The final text content.

Type ResponseOutputTextDone

The event type, must be response.output_text.done.

type SessionCreatedEvent struct{…}

Returned when a Session is created. Emitted automatically when a new connection is established as the first server event. This event will contain the default Session configuration.

EventID string

The unique ID of the server event.

Session SessionCreatedEventSessionUnion

The session configuration.

Accepts one of the following:
type RealtimeSessionCreateRequest struct{…}

Realtime session object configuration.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeAudioConfigoptional

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Model RealtimeSessionCreateRequestModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionCreateRequestModel
Accepts one of the following:
const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"
const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"
const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Tools RealtimeToolsConfigoptional

Tools available to the model.

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeTranscriptionSessionCreateRequest struct{…}

Realtime transcription session object configuration.

Type Transcription

The type of session to create. Always transcription for transcription sessions.

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Type SessionCreated

The event type, must be session.created.

type SessionUpdateEvent struct{…}

Send this event to update the session’s configuration. The client may send this event at any time to update any field except for voice and model. voice can be updated only if there have been no other audio outputs yet.

When the server receives a session.update, it will respond with a session.updated event showing the full, effective configuration. Only the fields that are present in the session.update are updated. To clear a field like instructions, pass an empty string. To clear a field like tools, pass an empty array. To clear a field like turn_detection, pass null.

Session SessionUpdateEventSessionUnion

Update the Realtime session. Choose either a realtime session or a transcription session.

Accepts one of the following:
type RealtimeSessionCreateRequest struct{…}

Realtime session object configuration.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeAudioConfigoptional

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Model RealtimeSessionCreateRequestModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionCreateRequestModel
Accepts one of the following:
const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"
const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"
const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Tools RealtimeToolsConfigoptional

Tools available to the model.

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeTranscriptionSessionCreateRequest struct{…}

Realtime transcription session object configuration.

Type Transcription

The type of session to create. Always transcription for transcription sessions.

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Type SessionUpdate

The event type, must be session.update.

EventID stringoptional

Optional client-generated ID used to identify this event. This is an arbitrary string that a client may assign. It will be passed back if there is an error with the event, but the corresponding session.updated event will not include it.

maxLength512
type SessionUpdatedEvent struct{…}

Returned when a session is updated with a session.update event, unless there is an error.

EventID string

The unique ID of the server event.

Session SessionUpdatedEventSessionUnion

The session configuration.

Accepts one of the following:
type RealtimeSessionCreateRequest struct{…}

Realtime session object configuration.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeAudioConfigoptional

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
Inf
Model RealtimeSessionCreateRequestModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
RealtimeSessionCreateRequestModel
Accepts one of the following:
const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"
const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"
const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Tools RealtimeToolsConfigoptional

Tools available to the model.

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeTranscriptionSessionCreateRequest struct{…}

Realtime transcription session object configuration.

Type Transcription

The type of session to create. Always transcription for transcription sessions.

Configuration for input and output audio.

Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Type SessionUpdated

The event type, must be session.updated.

type TranscriptionSessionUpdate struct{…}

Send this event to update a transcription session.

Session TranscriptionSessionUpdateSession

Realtime transcription session object configuration.

Include []stringoptional

The set of items to include in the transcription. Current available items are: item.input_audio_transcription.logprobs

InputAudioFormat stringoptional

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

Accepts one of the following:
const TranscriptionSessionUpdateSessionInputAudioFormatPcm16 TranscriptionSessionUpdateSessionInputAudioFormat = "pcm16"
const TranscriptionSessionUpdateSessionInputAudioFormatG711Ulaw TranscriptionSessionUpdateSessionInputAudioFormat = "g711_ulaw"
const TranscriptionSessionUpdateSessionInputAudioFormatG711Alaw TranscriptionSessionUpdateSessionInputAudioFormat = "g711_alaw"
InputAudioNoiseReduction TranscriptionSessionUpdateSessionInputAudioNoiseReductionoptional

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Type NoiseReductionTypeoptional

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

InputAudioTranscription AudioTranscriptionoptional

Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

TurnDetection TranscriptionSessionUpdateSessionTurnDetectionoptional

Configuration for turn detection. Can be set to null to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

PrefixPaddingMs int64optional

Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

SilenceDurationMs int64optional

Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Threshold float64optional

Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

Type stringoptional

Type of turn detection. Only server_vad is currently supported for transcription sessions.

Type TranscriptionSessionUpdate

The event type, must be transcription_session.update.

EventID stringoptional

Optional client-generated ID used to identify this event.

type TranscriptionSessionUpdatedEvent struct{…}

Returned when a transcription session is updated with a transcription_session.update event, unless there is an error.

EventID string

The unique ID of the server event.

Session TranscriptionSessionUpdatedEventSession

A new Realtime transcription session configuration.

When a session is created on the server via REST API, the session object also contains an ephemeral key. Default TTL for keys is 10 minutes. This property is not present when a session is updated via the WebSocket API.

ClientSecret TranscriptionSessionUpdatedEventSessionClientSecret

Ephemeral key returned by the API. Only present when the session is created on the server via REST API.

ExpiresAt int64

Timestamp for when the token expires. Currently, all tokens expire after one minute.

Value string

Ephemeral key usable in client environments to authenticate connections to the Realtime API. Use this in client-side environments rather than a standard API token, which should only be used server-side.

InputAudioFormat stringoptional

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.

InputAudioTranscription AudioTranscriptionoptional

Configuration of the transcription model.

Modalities []stringoptional

The set of modalities the model can respond with. To disable audio, set this to ["text"].

Accepts one of the following:
const TranscriptionSessionUpdatedEventSessionModalityText TranscriptionSessionUpdatedEventSessionModality = "text"
const TranscriptionSessionUpdatedEventSessionModalityAudio TranscriptionSessionUpdatedEventSessionModality = "audio"
TurnDetection TranscriptionSessionUpdatedEventSessionTurnDetectionoptional

Configuration for turn detection. Can be set to null to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

PrefixPaddingMs int64optional

Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

SilenceDurationMs int64optional

Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Threshold float64optional

Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

Type stringoptional

Type of turn detection, only server_vad is currently supported.

Type TranscriptionSessionUpdated

The event type, must be transcription_session.updated.

RealtimeClient Secrets

Create client secret
client.Realtime.ClientSecrets.New(ctx, body) (*ClientSecretNewResponse, error)
POST/realtime/client_secrets
ModelsExpand Collapse
type RealtimeSessionClientSecret struct{…}

Ephemeral key returned by the API.

ExpiresAt int64

Timestamp for when the token expires. Currently, all tokens expire after one minute.

Value string

Ephemeral key usable in client environments to authenticate connections to the Realtime API. Use this in client-side environments rather than a standard API token, which should only be used server-side.

type RealtimeSessionCreateResponse struct{…}

A new Realtime session configuration, with an ephemeral key. Default TTL for keys is one minute.

Ephemeral key returned by the API.

Type Realtime

The type of session to create. Always realtime for the Realtime API.

Audio RealtimeSessionCreateResponseAudiooptional

Configuration for input and output audio.

Input RealtimeSessionCreateResponseAudioInputoptional

The format of the input audio.

NoiseReduction RealtimeSessionCreateResponseAudioInputNoiseReductionoptional

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Type NoiseReductionTypeoptional

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

Transcription AudioTranscriptionoptional

Configuration for input audio transcription, defaults to off and can be set to null to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through the /audio/transcriptions endpoint and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

TurnDetection RealtimeSessionCreateResponseAudioInputTurnDetectionUnionoptional

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

Accepts one of the following:
type RealtimeSessionCreateResponseAudioInputTurnDetectionServerVad struct{…}

Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence.

Type ServerVad

Type of turn detection, server_vad to turn on simple Server VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs. If interrupt_response is set to false this may fail to create a response if the model is already responding.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

IdleTimeoutMs int64optional

Optional timeout after which a model response will be triggered automatically. This is useful for situations in which a long pause from the user is unexpected, such as a phone call. The model will effectively prompt the user to continue the conversation based on the current context.

The timeout value will be applied after the last model response's audio has finished playing, i.e. it's set to the response.done time plus audio playback duration.

An input_audio_buffer.timeout_triggered event (plus events associated with the Response) will be emitted when the timeout is reached. Idle timeout is currently only supported for server_vad mode.

minimum5000
maximum30000
InterruptResponse booloptional

Whether or not to automatically interrupt (cancel) any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs. If true then the response will be cancelled, otherwise it will continue until complete.

If both create_response and interrupt_response are set to false, the model will never respond automatically but VAD events will still be emitted.

PrefixPaddingMs int64optional

Used only for server_vad mode. Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

SilenceDurationMs int64optional

Used only for server_vad mode. Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Threshold float64optional

Used only for server_vad mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

type RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVad struct{…}

Server-side semantic turn detection which uses a model to determine when the user has finished speaking.

Type SemanticVad

Type of turn detection, semantic_vad to turn on Semantic VAD.

CreateResponse booloptional

Whether or not to automatically generate a response when a VAD stop event occurs.

Eagerness stringoptional

Used only for semantic_vad mode. The eagerness of the model to respond. low will wait longer for the user to continue speaking, high will respond more quickly. auto is the default and is equivalent to medium. low, medium, and high have max timeouts of 8s, 4s, and 2s respectively.

Accepts one of the following:
const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessLow RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "low"
const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "medium"
const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "high"
const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "auto"
InterruptResponse booloptional

Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs.

Output RealtimeSessionCreateResponseAudioOutputoptional

The format of the output audio.

Speed float64optional

The speed of the model's spoken response as a multiple of the original speed. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.

This parameter is a post-processing adjustment to the audio after it is generated, it's also possible to prompt the model to speak faster or slower.

maximum1.5
minimum0.25
Voice stringoptional

The voice the model uses to respond. Voice cannot be changed during the session once the model has responded with audio at least once. Current voice options are alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, and cedar. We recommend marin and cedar for best quality.

Accepts one of the following:
string
string
Accepts one of the following:
const RealtimeSessionCreateResponseAudioOutputVoiceAlloy RealtimeSessionCreateResponseAudioOutputVoice = "alloy"
const RealtimeSessionCreateResponseAudioOutputVoiceAsh RealtimeSessionCreateResponseAudioOutputVoice = "ash"
const RealtimeSessionCreateResponseAudioOutputVoiceBallad RealtimeSessionCreateResponseAudioOutputVoice = "ballad"
const RealtimeSessionCreateResponseAudioOutputVoiceCoral RealtimeSessionCreateResponseAudioOutputVoice = "coral"
const RealtimeSessionCreateResponseAudioOutputVoiceEcho RealtimeSessionCreateResponseAudioOutputVoice = "echo"
const RealtimeSessionCreateResponseAudioOutputVoiceSage RealtimeSessionCreateResponseAudioOutputVoice = "sage"
const RealtimeSessionCreateResponseAudioOutputVoiceShimmer RealtimeSessionCreateResponseAudioOutputVoice = "shimmer"
const RealtimeSessionCreateResponseAudioOutputVoiceVerse RealtimeSessionCreateResponseAudioOutputVoice = "verse"
const RealtimeSessionCreateResponseAudioOutputVoiceMarin RealtimeSessionCreateResponseAudioOutputVoice = "marin"
const RealtimeSessionCreateResponseAudioOutputVoiceCedar RealtimeSessionCreateResponseAudioOutputVoice = "cedar"
Include []stringoptional

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

Instructions stringoptional

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

MaxOutputTokens RealtimeSessionCreateResponseMaxOutputTokensUnionoptional

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.

Accepts one of the following:
int64
type Inf string
Model RealtimeSessionCreateResponseModeloptional

The Realtime model used for this session.

Accepts one of the following:
string
type RealtimeSessionCreateResponseModel string

The Realtime model used for this session.

Accepts one of the following:
const RealtimeSessionCreateResponseModelGPTRealtime RealtimeSessionCreateResponseModel = "gpt-realtime"
const RealtimeSessionCreateResponseModelGPTRealtime2025_08_28 RealtimeSessionCreateResponseModel = "gpt-realtime-2025-08-28"
const RealtimeSessionCreateResponseModelGPT4oRealtimePreview RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview"
const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2024-10-01"
const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2024-12-17"
const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2025-06-03"
const RealtimeSessionCreateResponseModelGPT4oMiniRealtimePreview RealtimeSessionCreateResponseModel = "gpt-4o-mini-realtime-preview"
const RealtimeSessionCreateResponseModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateResponseModel = "gpt-4o-mini-realtime-preview-2024-12-17"
const RealtimeSessionCreateResponseModelGPTRealtimeMini RealtimeSessionCreateResponseModel = "gpt-realtime-mini"
const RealtimeSessionCreateResponseModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateResponseModel = "gpt-realtime-mini-2025-10-06"
const RealtimeSessionCreateResponseModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateResponseModel = "gpt-realtime-mini-2025-12-15"
const RealtimeSessionCreateResponseModelGPTAudioMini RealtimeSessionCreateResponseModel = "gpt-audio-mini"
const RealtimeSessionCreateResponseModelGPTAudioMini2025_10_06 RealtimeSessionCreateResponseModel = "gpt-audio-mini-2025-10-06"
const RealtimeSessionCreateResponseModelGPTAudioMini2025_12_15 RealtimeSessionCreateResponseModel = "gpt-audio-mini-2025-12-15"
OutputModalities []stringoptional

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

Accepts one of the following:
const RealtimeSessionCreateResponseOutputModalityText RealtimeSessionCreateResponseOutputModality = "text"
const RealtimeSessionCreateResponseOutputModalityAudio RealtimeSessionCreateResponseOutputModality = "audio"
Prompt ResponsePromptoptional

Reference to a prompt template and its variables. Learn more.

ToolChoice RealtimeSessionCreateResponseToolChoiceUnionoptional

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

Accepts one of the following:
type ToolChoiceOptions string

Controls which (if any) tool is called by the model.

none means the model will not call any tool and instead generates a message.

auto means the model can pick between generating a message or calling one or more tools.

required means the model must call one or more tools.

Accepts one of the following:
const ToolChoiceOptionsNone ToolChoiceOptions = "none"
const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"
const ToolChoiceOptionsRequired ToolChoiceOptions = "required"
type ToolChoiceFunction struct{…}

Use this option to force the model to call a specific function.

Name string

The name of the function to call.

Type Function

For function calling, the type is always function.

type ToolChoiceMcp struct{…}

Use this option to force the model to call a specific tool on a remote MCP server.

ServerLabel string

The label of the MCP server to use.

Type Mcp

For MCP tools, the type is always mcp.

Name stringoptional

The name of the tool to call on the server.

Tools []RealtimeSessionCreateResponseToolUnionoptional

Tools available to the model.

Accepts one of the following:
type RealtimeFunctionTool struct{…}
Description stringoptional

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

Name stringoptional

The name of the function.

Parameters anyoptional

Parameters of the function in JSON Schema.

Type RealtimeFunctionToolTypeoptional

The type of the tool, i.e. function.

type RealtimeSessionCreateResponseToolMcpTool struct{…}

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

ServerLabel string

A label for this MCP server, used to identify it in tool calls.

Type Mcp

The type of the MCP tool. Always mcp.

AllowedTools RealtimeSessionCreateResponseToolMcpToolAllowedToolsUnionoptional

List of allowed tool names or a filter object.

Accepts one of the following:
type RealtimeSessionCreateResponseToolMcpToolAllowedToolsMcpAllowedTools []string

A string array of allowed tool names

type RealtimeSessionCreateResponseToolMcpToolAllowedToolsMcpToolFilter struct{…}

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Authorization stringoptional

An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.

ConnectorID stringoptional

Identifier for service connectors, like those available in ChatGPT. One of server_url or connector_id must be provided. Learn more about service connectors here.

Currently supported connector_id values are:

  • Dropbox: connector_dropbox
  • Gmail: connector_gmail
  • Google Calendar: connector_googlecalendar
  • Google Drive: connector_googledrive
  • Microsoft Teams: connector_microsoftteams
  • Outlook Calendar: connector_outlookcalendar
  • Outlook Email: connector_outlookemail
  • SharePoint: connector_sharepoint
Accepts one of the following:
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorDropbox RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_dropbox"
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGmail RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_gmail"
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGooglecalendar RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_googlecalendar"
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGoogledrive RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_googledrive"
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorMicrosoftteams RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_microsoftteams"
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorOutlookcalendar RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_outlookcalendar"
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorOutlookemail RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_outlookemail"
const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorSharepoint RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_sharepoint"
Headers map[string, string]optional

Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.

RequireApproval RealtimeSessionCreateResponseToolMcpToolRequireApprovalUnionoptional

Specify which of the MCP server's tools require approval.

Accepts one of the following:
type RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilter struct{…}

Specify which of the MCP server's tools require approval. Can be always, never, or a filter object associated with tools that require approval.

Always RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilterAlwaysoptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

Never RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilterNeveroptional

A filter object to specify which tools are allowed.

ReadOnly booloptional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

ToolNames []stringoptional

List of allowed tool names.

type RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting string

Specify a single approval policy for all tools. One of always or never. When set to always, all tools will require approval. When set to never, all tools will not require approval.

Accepts one of the following:
const RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting = "always"
const RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting = "never"
ServerDescription stringoptional

Optional description of the MCP server, used to provide more context.

ServerURL stringoptional

The URL for the MCP server. One of server_url or connector_id must be provided.

Tracing RealtimeSessionCreateResponseTracingUnionoptional

Realtime API can write session traces to the Traces Dashboard. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

Accepts one of the following:
type Auto string

Enables tracing and sets default values for tracing configuration options. Always auto.

type RealtimeSessionCreateResponseTracingTracingConfiguration struct{…}

Granular configuration for tracing.

GroupID stringoptional

The group id to attach to this trace to enable filtering and grouping in the Traces Dashboard.

Metadata anyoptional

The arbitrary metadata to attach to this trace to enable filtering in the Traces Dashboard.

WorkflowName stringoptional

The name of the workflow to attach to this trace. This is used to name the trace in the Traces Dashboard.

Truncation RealtimeTruncationUnionoptional

When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.

type RealtimeTranscriptionSessionCreateResponse struct{…}

A Realtime transcription session configuration object.

ID string

Unique identifier for the session that looks like sess_1234567890abcdef.

Object string

The object type. Always realtime.transcription_session.

Type Transcription

The type of session. Always transcription for transcription sessions.

Audio RealtimeTranscriptionSessionCreateResponseAudiooptional

Configuration for input audio for the session.

Input RealtimeTranscriptionSessionCreateResponseAudioInputoptional

The PCM audio format. Only a 24kHz sample rate is supported.

NoiseReduction RealtimeTranscriptionSessionCreateResponseAudioInputNoiseReductionoptional

Configuration for input audio noise reduction.

Type NoiseReductionTypeoptional

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

Transcription AudioTranscriptionoptional

Configuration of the transcription model.

Configuration for turn detection. Can be set to null to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

ExpiresAt int64optional

Expiration timestamp for the session, in seconds since epoch.

Include []stringoptional

Additional fields to include in server outputs.

  • item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.
type RealtimeTranscriptionSessionTurnDetection struct{…}

Configuration for turn detection. Can be set to null to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

PrefixPaddingMs int64optional

Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

SilenceDurationMs int64optional

Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Threshold float64optional

Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

Type stringoptional

Type of turn detection, only server_vad is currently supported.

RealtimeCalls

Accept call
client.Realtime.Calls.Accept(ctx, callID, body) error
POST/realtime/calls/{call_id}/accept
Hang up call
client.Realtime.Calls.Hangup(ctx, callID) error
POST/realtime/calls/{call_id}/hangup
Refer call
client.Realtime.Calls.Refer(ctx, callID, body) error
POST/realtime/calls/{call_id}/refer
Reject call
client.Realtime.Calls.Reject(ctx, callID, body) error
POST/realtime/calls/{call_id}/reject

RealtimeSessions

RealtimeTranscription Sessions