Skip to content

Client Secrets

Create client secret
POST/realtime/client_secrets
ModelsExpand Collapse
RealtimeSessionClientSecret = object { expires_at, value }

Ephemeral key returned by the API.

expires_at: number

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.

RealtimeSessionCreateResponse = object { client_secret, type, audio, 10 more }

A new Realtime session configuration, with an ephemeral key. Default TTL for keys is one minute.

client_secret: RealtimeSessionClientSecret { expires_at, value }

Ephemeral key returned by the API.

type: "realtime"

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

audio: optional object { input, output }

Configuration for input and output audio.

input: optional object { format, noise_reduction, transcription, turn_detection }
format: optional RealtimeAudioFormats

The format of the input audio.

noise_reduction: optional object { type }

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: optional NoiseReductionType

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: optional AudioTranscription { language, model, prompt }

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.

turn_detection: optional object { type, create_response, idle_timeout_ms, 4 more } or object { type, create_response, eagerness, interrupt_response }

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:
ServerVad = object { type, create_response, idle_timeout_ms, 4 more }

Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence.

type: "server_vad"

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

create_response: optional boolean

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.

idle_timeout_ms: optional number

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
interrupt_response: optional boolean

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.

prefix_padding_ms: optional number

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

silence_duration_ms: optional number

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: optional number

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.

SemanticVad = object { type, create_response, eagerness, interrupt_response }

Server-side semantic turn detection which uses a model to determine when the user has finished speaking.

type: "semantic_vad"

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

create_response: optional boolean

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

eagerness: optional "low" or "medium" or "high" or "auto"

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:
"low"
"medium"
"high"
"auto"
interrupt_response: optional boolean

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: optional object { format, speed, voice }
format: optional RealtimeAudioFormats

The format of the output audio.

speed: optional number

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: optional string or "alloy" or "ash" or "ballad" or 7 more

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:
UnionMember0 = string
UnionMember1 = "alloy" or "ash" or "ballad" or 7 more

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:
"alloy"
"ash"
"ballad"
"coral"
"echo"
"sage"
"shimmer"
"verse"
"marin"
"cedar"
include: optional array of "item.input_audio_transcription.logprobs"

Additional fields to include in server outputs.

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

instructions: optional string

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.

max_output_tokens: optional number or "inf"

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:
UnionMember0 = number
UnionMember1 = "inf"
model: optional string or "gpt-realtime" or "gpt-realtime-2025-08-28" or "gpt-4o-realtime-preview" or 11 more

The Realtime model used for this session.

Accepts one of the following:
UnionMember0 = string
UnionMember1 = "gpt-realtime" or "gpt-realtime-2025-08-28" or "gpt-4o-realtime-preview" or 11 more

The Realtime model used for this session.

Accepts one of the following:
"gpt-realtime"
"gpt-realtime-2025-08-28"
"gpt-4o-realtime-preview"
"gpt-4o-realtime-preview-2024-10-01"
"gpt-4o-realtime-preview-2024-12-17"
"gpt-4o-realtime-preview-2025-06-03"
"gpt-4o-mini-realtime-preview"
"gpt-4o-mini-realtime-preview-2024-12-17"
"gpt-realtime-mini"
"gpt-realtime-mini-2025-10-06"
"gpt-realtime-mini-2025-12-15"
"gpt-audio-mini"
"gpt-audio-mini-2025-10-06"
"gpt-audio-mini-2025-12-15"
output_modalities: optional array of "text" or "audio"

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:
"text"
"audio"
prompt: optional ResponsePrompt { id, variables, version }

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

tool_choice: optional ToolChoiceOptions or ToolChoiceFunction { name, type } or ToolChoiceMcp { server_label, type, name }

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

Accepts one of the following:
ToolChoiceOptions = "none" or "auto" or "required"

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:
"none"
"auto"
"required"
ToolChoiceFunction = object { name, type }

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.

ToolChoiceMcp = object { server_label, type, name }

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

server_label: string

The label of the MCP server to use.

type: "mcp"

For MCP tools, the type is always mcp.

name: optional string

The name of the tool to call on the server.

tools: optional array of RealtimeFunctionTool { description, name, parameters, type } or object { server_label, type, allowed_tools, 6 more }

Tools available to the model.

Accepts one of the following:
RealtimeFunctionTool = object { description, name, parameters, type }
description: optional string

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: optional string

The name of the function.

parameters: optional unknown

Parameters of the function in JSON Schema.

type: optional "function"

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

McpTool = object { server_label, type, allowed_tools, 6 more }

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

server_label: string

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

type: "mcp"

The type of the MCP tool. Always mcp.

allowed_tools: optional array of string or object { read_only, tool_names }

List of allowed tool names or a filter object.

Accepts one of the following:
McpAllowedTools = array of string

A string array of allowed tool names

McpToolFilter = object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional boolean

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.

tool_names: optional array of string

List of allowed tool names.

authorization: optional string

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.

connector_id: optional "connector_dropbox" or "connector_gmail" or "connector_googlecalendar" or 5 more

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:
"connector_dropbox"
"connector_gmail"
"connector_googlecalendar"
"connector_googledrive"
"connector_microsoftteams"
"connector_outlookcalendar"
"connector_outlookemail"
"connector_sharepoint"
headers: optional map[string]

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

require_approval: optional object { always, never } or "always" or "never"

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

Accepts one of the following:
McpToolApprovalFilter = object { always, never }

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: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional boolean

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.

tool_names: optional array of string

List of allowed tool names.

never: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional boolean

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.

tool_names: optional array of string

List of allowed tool names.

McpToolApprovalSetting = "always" or "never"

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:
"always"
"never"
server_description: optional string

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

server_url: optional string

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

tracing: optional "auto" or object { group_id, metadata, workflow_name }

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 = "auto"

Enables tracing and sets default values for tracing configuration options. Always auto.

TracingConfiguration = object { group_id, metadata, workflow_name }

Granular configuration for tracing.

group_id: optional string

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

metadata: optional unknown

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

workflow_name: optional string

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

truncation: optional RealtimeTruncation

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.

RealtimeTranscriptionSessionCreateResponse = object { id, object, type, 3 more }

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: optional object { input }

Configuration for input audio for the session.

input: optional object { format, noise_reduction, transcription, turn_detection }
format: optional RealtimeAudioFormats

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

noise_reduction: optional object { type }

Configuration for input audio noise reduction.

type: optional NoiseReductionType

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: optional AudioTranscription { language, model, prompt }

Configuration of the transcription model.

turn_detection: optional RealtimeTranscriptionSessionTurnDetection { prefix_padding_ms, silence_duration_ms, threshold, type }

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.

expires_at: optional number

Expiration timestamp for the session, in seconds since epoch.

include: optional array of "item.input_audio_transcription.logprobs"

Additional fields to include in server outputs.

  • item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.
RealtimeTranscriptionSessionTurnDetection = object { prefix_padding_ms, silence_duration_ms, threshold, type }

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.

prefix_padding_ms: optional number

Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

silence_duration_ms: optional number

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: optional number

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: optional string

Type of turn detection, only server_vad is currently supported.