Server events

Events sent by the server as JSON text frames. Every server event carries a server-generated event_id (string) and a type.

Session and conversation

`session.created`

Sent in response to the first session.update. Contains the session id — read yours from session.id.

object

The acknowledged session configuration, plus id (string) and object: "realtime.session".

`session.updated`

Acknowledges each session.update after the first.

object

Same shape as in session.created.

`conversation.item.added`

An item entered the conversation — user turns, assistant replies, tool calls and results, and client-created items alike.

object

The conversation item.

string | null

Id of the item immediately before this one; null for the first item.

`conversation.item.retrieved`

Answer to conversation.item.retrieve.

object

The requested conversation item.

`conversation.item.truncated`

Acknowledges conversation.item.truncate, echoing its fields.

string

Id of the truncated item.

integer

Index of the truncated content part.

integer

Cut position in milliseconds (0 for the text-only no-op).

`conversation.item.deleted`

Acknowledges conversation.item.delete.

string

Id of the removed item.

`conversation.context.summarized`

With truncation: "auto", older conversation items were condensed into a summary to stay within the model’s context window. The summarized items remain retrievable via conversation.item.retrieve. Extension; not part of the OpenAI Realtime API — clients built on OpenAI SDK event types should tolerate this unknown event type.

string

The summary text.

array of string

Ids of the items condensed into the summary.

string

Id of the new summary item.

integer

Context token count before summarization.

integer

Context token count after summarization.

Input audio

`input_audio_buffer.speech_started`

Server VAD detected the start of user speech. If the assistant is speaking, this is the barge-in signal — stop local playback.

string

Id of the user item this speech will be added to.

integer

Position in the input audio stream, in milliseconds, where speech begins (includes prefix_padding_ms).

`input_audio_buffer.speech_stopped`

Server VAD detected the end of user speech; a response follows automatically.

string

Id of the user item.

integer

Position in the input audio stream, in milliseconds, where speech ends.

`input_audio_buffer.committed`

The input buffer was committed as a user item — after a client input_audio_buffer.commit.

string

Id of the user item the audio was committed to.

string | null

Id of the item before it, or null.

`input_audio_buffer.cleared`

Acknowledges input_audio_buffer.clear. No fields beyond event_id and type.

`conversation.item.input_audio_transcription.completed`

Final transcript of a user audio turn. Only emitted when audio.input.transcription.model is configured (higgs-stt-3.1); when unset, no transcription events are emitted.

string

Id of the user item the transcript belongs to.

integer

Index of the audio content part that was transcribed.

string

The transcript text.

Response lifecycle

`response.created`

Response generation started.

object

The response object with status: "in_progress". Its metadata echoes the metadata from your response.create, letting you correlate this response with the request that triggered it (null when none was sent, e.g. VAD-triggered responses).

`response.output_item.added`

An output item (assistant message or tool call) was added to the response.

string

Id of the response.

integer

Index of the item in the response output.

object

The conversation item.

`response.output_item.done`

An output item finished streaming. Fields as in response.output_item.added, with the completed item.

`response.content_part.added`

A content part started streaming within an output item.

string

Id of the response.

string

Id of the output item.

integer

Index of the item in the response output.

integer

Index of the part within the item’s content.

object

Content part: type ("text" | "audio"), audio (string, base64, or null), transcript (string or null).

`response.content_part.done`

A content part finished streaming. Fields as in response.content_part.added, with the completed part.

`response.output_audio.delta`

A chunk of output audio, encoded in the configured audio.output.format.

string

Id of the response.

string

Id of the output item.

integer

Index of the item in the response output.

integer

Index of the audio content part.

string

Base64-encoded audio chunk.

`response.output_audio.done`

The audio stream for a content part completed. Same fields as response.output_audio.delta, without delta.

`response.output_audio_transcript.delta`

Streaming transcript of the audio the assistant is speaking.

string

Id of the response.

string

Id of the output item.

integer

Index of the item in the response output.

integer

Index of the content part.

string

Transcript text fragment.

`response.output_audio_transcript.length`

A transcript fragment annotated with the duration of its corresponding audio — useful for aligning captions with playback. Extension; not part of the OpenAI schema.

string

Id of the response.

string

Id of the output item.

integer

Index of the item in the response output.

integer

Index of the content part.

string

Transcript text fragment.

integer

Duration in milliseconds of the audio corresponding to delta.

`response.output_audio_transcript.done`

The spoken transcript for a content part is complete.

string

Id of the response.

string

Id of the output item.

integer

Index of the item in the response output.

integer

Index of the content part.

string

The full transcript of the spoken audio.

`response.output_text.delta`

A fragment of streamed text output. Emitted instead of audio events when output_modalities is ["text"].

string

Id of the response.

string

Id of the output item.

integer

Index of the item in the response output.

integer

Index of the content part.

string

Text fragment.

`response.output_text.done`

The text output for a content part is complete. Note this event carries no item_id — correlate via response.output_item.done.

string

Id of the response.

integer

Index of the item in the response output.

integer

Index of the content part.

string

The full text output.

`response.function_call_arguments.delta`

Streaming fragment of a tool call’s arguments.

string

Id of the response.

string

Id of the function_call item.

integer

Index of the item in the response output.

string

Id of the tool call; echo it in function_call_output.

string

JSON arguments fragment.

`response.function_call_arguments.done`

A tool call’s arguments are complete. Execute the function and return the result via conversation.item.create (function_call_output), then send response.create.

string

Id of the response.

string

Id of the function_call item.

integer

Index of the item in the response output.

string

Name of the function to call.

string

Id of the tool call; echo it in function_call_output.

string

Complete JSON-encoded arguments.

`response.done`

The response finished. Emitted exactly once per response_id. A response that ends in a tool call carries the completed function_call item in response.output.

object

The response object. status is completed or cancelled (interrupted / response.cancel). The schema also defines incomplete and failed, but the server does not currently emit them.

Session control and status

`error`

Something went wrong. Billing refusals use error.type: "insufficient_quota" and precede WebSocket close code 4429.

object

type (string, error category), code (string or null), message (string, human-readable), param (string or null).

`session.idle_timeout`

No user speech for the idle window (5 minutes). The session closes after this event.

integer

Seconds without detected user speech.

`session.max_duration_reached`

The session reached its server-enforced wall-clock cap. The session closes after this event.

integer

The enforced maximum session duration, in seconds.

Data types

Conversation items

All items have id, object: "realtime.item", and a type:

Type	Fields	Notes
`message` (role `user`)	`content[]` of `input_text` / `input_audio`, `status`	Client-created messages carry `input_text` content; spoken turns carry audio with the transcript filled in as it completes.
`message` (role `assistant`)	`content[]` of `text` / `audio` (with `transcript`), `status`
`function_call`	`call_id`, `name`, `arguments`, `status`, `executor` (`"client"`)	A tool call for your client to execute.
`function_call_output`	`call_id`, `output`, `status`	Sent by the client with the tool’s result.

Response object

{
  "id": "resp_...",
  "object": "realtime.response",
  "status": "completed",
  "status_details": null,
  "output": [],
  "usage": null,
  "metadata": null
}

status is in_progress (on response.created), then completed or cancelled (on response.done).
status_details is defined in the schema ({"type": "cancelled", "reason": "turn_detected" | "client_cancelled"}, {"type": "incomplete", "reason": "max_output_tokens" | "content_filter"}, {"type": "failed", "error": {"code", "message"}}) but is currently always sent as null.
usage ({"total_tokens", "input_tokens", "output_tokens"}) is currently always sent as null.
metadata is echoed on response.created only; response.done carries metadata: null.

Client events

The events you send that trigger these.

Audio and voices

Decode response.output_audio.delta in the format you configured.

Turn detection and interruptions

Handling speech_started as the barge-in signal.

Tool use

Acting on response.function_call_arguments.done.

​Session and conversation

​session.created

​session.updated

​conversation.item.added

​conversation.item.retrieved

​conversation.item.truncated

​conversation.item.deleted

​conversation.context.summarized

​Input audio

​input_audio_buffer.speech_started

​input_audio_buffer.speech_stopped

​input_audio_buffer.committed

​input_audio_buffer.cleared

​conversation.item.input_audio_transcription.completed

​Response lifecycle

​response.created

​response.output_item.added

​response.output_item.done

​response.content_part.added

​response.content_part.done

​response.output_audio.delta

​response.output_audio.done

​response.output_audio_transcript.delta

​response.output_audio_transcript.length

​response.output_audio_transcript.done

​response.output_text.delta

​response.output_text.done

​response.function_call_arguments.delta

​response.function_call_arguments.done

​response.done

​Session control and status

​error

​session.idle_timeout

​session.max_duration_reached

​Data types

​Conversation items

​Response object

​Related

Client events

Audio and voices

Turn detection and interruptions

Tool use

Session and conversation

`session.created`

`session.updated`

`conversation.item.added`

`conversation.item.retrieved`

`conversation.item.truncated`

`conversation.item.deleted`

`conversation.context.summarized`

Input audio

`input_audio_buffer.speech_started`

`input_audio_buffer.speech_stopped`

`input_audio_buffer.committed`

`input_audio_buffer.cleared`

`conversation.item.input_audio_transcription.completed`

Response lifecycle

`response.created`

`response.output_item.added`

`response.output_item.done`

`response.content_part.added`

`response.content_part.done`

`response.output_audio.delta`

`response.output_audio.done`

`response.output_audio_transcript.delta`

`response.output_audio_transcript.length`

`response.output_audio_transcript.done`

`response.output_text.delta`

`response.output_text.done`

`response.function_call_arguments.delta`

`response.function_call_arguments.done`

`response.done`

Session control and status

`error`

`session.idle_timeout`

`session.max_duration_reached`

Data types

Conversation items

Response object

Related