Live

ModelsExpand Collapse

audio_format: object { rate, type } or object { rate, type } or object { rate, type }

Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately.

built_in_voice: "alloy" or "ash" or "ballad" or 19 more

A built-in voice available for Live speech.

client_config: object { data_channel }

Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected.

client_delegation: object { type }

Delegate tasks to your application. The Live session emits delegation events that your backend handles.

client_event: SessionStartEvent { session, type, event_id } or SessionUpdateEvent { session, type, event_id } or InputAudioAppendEvent { audio, type, event_id } or 8 more

Client events for Live. Initialize a primary WebSocket with session.start and wait for session.started. WebRTC creation already starts the session. Audio append is primary WebSocket-only. See the Live prompting guide before writing frontend instructions and delegation policies.

commentary_append_event: object { content, delegation_id, type, event_id }

Provide context the Live model can communicate to the user, optionally for an existing client delegation.

commentary_appended_event: object { end_ms, event_id, start_ms, 2 more }

Returned when a session.commentary.append command is accepted into the Live session timeline. Acknowledges the added commentary without guaranteeing exact wording or completed audio playback.

custom_voice: object { id }

data_channel_config: object { allowed_client_events, allowed_server_events }

Control which Live events an untrusted WebRTC frontend can send and receive over its data channel. These restrictions do not apply to trusted sideband connections.

delegation_created_event: object { delegation, event_id, offset_ms, 2 more }

Returned when the Live model delegates work to your application or a Responses backend. Contains delegation metadata and the position on the session timeline where the work was delegated.

error: object { code, message, type, 2 more }

Details of an error encountered by the Live session, including the affected parameter or client command when available.

error_event: object { error, event_id, type, client_event_id }

Reports an error in the Live session, such as an invalid client command. Use error.client_event_id, when present, to identify the command that caused the error.

fork_session_config: object { audio, client, delegation, store }

Overrides for a stored session after connecting to the fork WebSocket. An empty object inherits the stored configuration; do not supply a new model. audio.format applies only to the new WebSocket connection. client overrides are only supported for WebRTC forks.

fork_session_start_event: object { session, type, event_id }

Start a Live session after connecting to a stored session’s fork WebSocket. Send an empty session object to use the stored configuration.

function_tool: object { name, type, description, 2 more }

A function tool available to the Responses backend when the Live model delegates a task.

info_event: object { code, event_id, message, 2 more }

An informational notice about the Live session, such as the event permissions applied to a frontend data channel.

initial_item: object { content, role, id, 2 more } or object { content, role, id, 2 more } or object { content, role, id, 2 more }

A developer, user, or assistant message supplied as text history before the Live session starts.

input_audio_append_event: object { audio, type, event_id }

Send audio to a Live session over its primary WebSocket. WebRTC and SIP sessions send audio over their media transport.

input_audio_mute_event: object { type, event_id }

Mute audio input to the Live model without closing the session. The server acknowledges with session.input_audio.muted.

input_audio_muted_event: object { event_id, type, client_event_id }

Returned when a session.input_audio.mute command is accepted. Input audio is no longer sent to the model; sideband audio reflection continues.

input_audio_unmute_event: object { type, event_id }

Resume audio input to a Live model after muting it. The server acknowledges with session.input_audio.unmuted.

input_audio_unmuted_event: object { event_id, type, client_event_id }

Returned when a session.input_audio.unmute command is accepted. Input audio is sent to the model again.

input_transcript_delta_event: object { delta, end_ms, event_id, 3 more }

A transcript fragment for user input audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event.

instructions_append_event: object { content, delegation_id, type, event_id }

Append instructions to the Live conversation while it is running, optionally associating them with an existing client delegation.

instructions_appended_event: object { end_ms, event_id, start_ms, 2 more }

Returned when a session.instructions.append command is accepted into the Live session timeline. Acknowledges the appended instructions without guaranteeing that the model has acted on them.

media_session_config: object { model, audio, client, 4 more }

Startup configuration for a Live media session. Follow the Live prompting guide when writing frontend instructions and the backend prompt under delegation.responses.instructions.

media_session_fork_config: object { client, delegation, store }

Optional overrides for a stored Live session. Omitted settings are inherited. The model, voice, frontend instructions, and prior conversation come from the stored session. WebRTC negotiates its audio format; audio.format is only supported on WebSocket forks.

output_audio_delta_event: object { delta, type, end_ms, start_ms }

An audio chunk generated by the Live model. Decode and play primary WebSocket chunks in delivery order using the configured session audio format. Sideband connections receive reflected output audio with timestamps.

output_transcript_delta_event: object { delta, end_ms, event_id, 3 more }

A transcript fragment for assistant output audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event.

response_create_event: object { type, event_id }

Request a response from the Live session’s Responses backend, or continue a delegated response waiting for tool results. Requires Responses delegation.

response_event: object { event, event_id, type, 2 more }

A streaming Responses API event from a backend delegated to by the Live session. Use the outer delegation_id to associate the nested stream with its Live delegation.

response_item_create_event: object { item, type, event_id }

Add an input item to the Live session’s Responses backend. Requires Responses delegation; use response.create to request a response.

responses_delegation_config: object { model, instructions, max_output_tokens, 6 more }

Model, prompt, and tool settings for tasks delegated by the Live session to a Responses backend.

responses_delegation_update_config: object { instructions, max_output_tokens, model, 6 more }

Updates to the Responses backend of an existing Live session. Omitted settings retain their current values.

server_event: SessionStartedEvent { event_id, session, type, client_event_id } or SessionUpdatedEvent { event_id, session, type, client_event_id } or InputAudioMutedEvent { event_id, type, client_event_id } or 19 more

Server events for Live. Response lifecycle events are wrapped inside response.event; dispatch the nested event by its full type and tolerate new response event types. Follow the Live prompting guide when designing the conversation and delegation policy.

server_event_selector: object { type, response_event }

A Live server event selector for the WebRTC frontend data channel.

session_close_event: object { type, event_id }

Request that the Live session close. The terminal session.closed event contains the close reason and final usage.

session_closed_event: object { event_id, reason, session, 3 more }

Returned after the Live session finishes finalizing, with the close reason, final session snapshot, and cumulative audio usage. A connection closing without this event does not confirm successful finalization.

session_config: object { model, audio, client, 4 more }

Initial configuration for a Live session, including its model, conversation instructions, audio, and delegated task handling.

session_resource: object { id, expires_at, model, 7 more }

The resolved Live session configuration and server-assigned session metadata.

session_start_event: object { session, type, event_id }

Start a Live session on a primary WebSocket. Send this event before other commands and wait for session.started.

session_started_event: object { event_id, session, type, client_event_id }

Returned when a Live session has started. Contains the resolved session configuration, including server defaults.

session_update_config: object { delegation }

Changes to an active Live session. Only delegation backend settings can be updated after startup.

session_update_event: object { session, type, event_id }

Update the delegation settings of an active Live session. The server acknowledges accepted changes with session.updated.

session_updated_event: object { event_id, session, type, client_event_id }

Returned when a Live session update is accepted. Contains the resolved session configuration after the update.

session_usage: object { seconds }

Cumulative audio duration for a Live session. Values are totals for the session, not increments to sum across usage events.

session_usage_updated_event: object { event_id, type, usage, 2 more }

Reports cumulative Live audio usage and, when available, the most recent context-window usage. Delegated Responses token usage is reported separately in response.event events.

thinking_append_event: object { content, delegation_id, type, event_id }

Provide silent reasoning or progress context to the Live model, optionally for an existing client delegation.

thinking_appended_event: object { end_ms, event_id, start_ms, 2 more }

Returned when a session.thinking.append command is accepted into the Live session timeline. Acknowledges the added reasoning context without guaranteeing any spoken output.

LiveForks

ModelsExpand Collapse

fork_client_event: ForkSessionStartEvent { session, type, event_id } or SessionUpdateEvent { session, type, event_id } or InputAudioAppendEvent { audio, type, event_id } or 8 more

Client events for a Live fork WebSocket. First send session.start with an overrides object (which may be empty), then wait for session.started before sending other commands. The model and conversation are inherited from the stored session.

fork_server_event: SessionStartedEvent { event_id, session, type, client_event_id } or SessionUpdatedEvent { event_id, session, type, client_event_id } or InputAudioMutedEvent { event_id, type, client_event_id } or 19 more

Suggested

Suggested

Live

ModelsExpand Collapse

LiveForks

ModelsExpand Collapse

LiveSessions

Accept call

Download recording

Fork session

Hang up session

Transfer call

Reject call

LiveSideband