Qwen-Audio-Realtime Server Events

Server events are pushed from the server to the client. All server events include the common fields event_id (a unique identifier automatically generated by the server) and type (the event type). User guide: Real-time voice conversation (Qwen-Audio-Realtime). For the event interaction timeline, see WebSocket API.

error

Returned when a request is invalid or a service error occurs. Client errors (invalid_request_error) do not interrupt the connection; server errors (server_error) terminate the connection.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `error`.
error	object	Error details.
error.type	string	Error type, such as `invalid_request_error` (client error) or `server_error` (server error).
error.code	string	Error code.
error.message	string	Error message.
error.param	string	The parameter related to the error.

{
    "event_id": "event_xxx",
    "type": "error",
    "error": {
        "type": "invalid_request_error",
        "code": "invalid_value",
        "message": "Cannot create response while another response is in progress.",
        "param": "response.create"
    }
}

session.created

The first event sent by the server after the connection is established, carrying the default session configuration.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `session.created`.
session	object	The session configuration.
session.object	string	Fixed as `realtime.session`.
session.model	string	The name of the model in use.
session.modalities	array	The model's output modalities.
session.voice	string	The voice used for generated audio — either a system voice name or the `voice_id` of a voice-cloning voice.
session.input_audio_transcription	object	Speech transcription configuration.
session.input_audio_transcription.model	string	The speech transcription model, such as `fun-asr`.
session.turn_detection	object	Turn detection (VAD) configuration.
session.id	string	The unique identifier of the session.

{
    "event_id": "event_KiKZC2zrhNsKFPZ5cTpyA",
    "type": "session.created",
    "session": {
        "object": "realtime.session",
        "model": "qwen-audio-3.0-realtime-plus",
        "modalities": ["text", "audio"],
        "voice": "longanqian",
        "input_audio_transcription": {
            "model": "fun-asr"
        },
        "turn_detection": {
            "type": "server_vad",
            "threshold": 0.5,
            "silence_duration_ms": 800
        },
        "id": "sess_A1LbG2D63WELBSawRbpq8"
    }
}

session.updated

Returned after a session.update request is processed successfully, carrying the complete updated session configuration. If an error occurs, an error event is returned instead.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `session.updated`.
session	object	The complete updated session configuration. The structure matches the `session` object in `session.created`.

{
    "event_id": "event_FMG6kiHbILCGiqXFPA98e",
    "type": "session.updated",
    "session": {
        "id": "sess_A1LbG2D63WELBSawRbpq8",
        "object": "realtime.session",
        "model": "qwen-audio-3.0-realtime-plus",
        "modalities": ["text", "audio"],
        "voice": "longanqian",
        "input_audio_transcription": {
            "model": "fun-asr"
        },
        "turn_detection": {
            "type": "smart_turn",
            "threshold": 0.1,
            "silence_duration_ms": 900
        }
    }
}

input_audio_buffer.speech_started

The VAD detected the start of speech (server_vad / smart_turn mode).

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `input_audio_buffer.speech_started`.
audio_start_ms	integer	The timestamp (in milliseconds) when speech started.
item_id	string	The ID of the item that will be created once this segment of speech is committed.

{
    "event_id": "event_xxx",
    "type": "input_audio_buffer.speech_started",
    "audio_start_ms": 1200,
    "item_id": "item_xxx"
}

input_audio_buffer.speech_stopped

The VAD detected the end of speech (server_vad / smart_turn mode).

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `input_audio_buffer.speech_stopped`.
audio_end_ms	integer	The timestamp (in milliseconds) when speech ended.
item_id	string	The ID of the user message item that will be created.
reason	string	Returned only in smart_turn mode. A value of `turn_invalid` indicates the current turn was judged invalid (no semantic content) and does not trigger inference. This field is not returned for valid turns.

{
    "event_id": "event_xxx",
    "type": "input_audio_buffer.speech_stopped",
    "audio_end_ms": 3400,
    "item_id": "item_xxx",
    "reason": "turn_invalid"
}

input_audio_buffer.committed

The audio buffer was committed as a user message (either via a push-to-talk commit or automatic VAD commit).

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `input_audio_buffer.committed`.
previous_item_id	string	The ID of the previous conversation item.
item_id	string	The ID of the created user message item.

{
    "event_id": "event_xxx",
    "type": "input_audio_buffer.committed",
    "previous_item_id": "item_xxx",
    "item_id": "item_xxx"
}

input_audio_buffer.cleared

The audio buffer was cleared (push-to-talk mode only).

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `input_audio_buffer.cleared`.

{
    "event_id": "event_xxx",
    "type": "input_audio_buffer.cleared"
}

conversation.item.created

A new conversation item was created successfully. Triggered when a user audio message is committed, the client manually creates an item, or an assistant response begins.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.created`.
previous_item_id	string	The ID of the previous conversation item.
item	object	The created conversation item.
item.id	string	The unique identifier of the conversation item.
item.object	string	Fixed as `realtime.item`.
item.type	string	The item type: `message` (a regular message) or `function_call` (a function call).
item.status	string	The item status, such as `in_progress` or `completed`.
item.role	string	The message role, such as `user` or `assistant`. Included only for `message` items.
item.content	array	The list of message content. Included only for `message` items.

{
    "event_id": "event_xxx",
    "type": "conversation.item.created",
    "previous_item_id": "item_xxx",
    "item": {
        "id": "item_xxx",
        "object": "realtime.item",
        "type": "message",
        "status": "in_progress",
        "role": "assistant",
        "content": []
    }
}

conversation.item.deleted

A conversation item was deleted. Returned as confirmation after the client sends conversation.item.delete.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.deleted`.
item_id	string	The ID of the deleted conversation item.

{
    "event_id": "event_xxx",
    "type": "conversation.item.deleted",
    "item_id": "item_xxx"
}

conversation.item.retrieved

A conversation item was retrieved successfully. Returned after the client sends conversation.item.retrieve. For audio-type content, only the transcript is returned, not the original audio data.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.retrieved`.
item	object	The complete retrieved conversation item.
item.id	string	The unique identifier of the conversation item.
item.object	string	Fixed as `realtime.item`.
item.type	string	The item type: `message` (a regular message) or `function_call` (a function call).
item.role	string	The message role, such as `user` or `assistant`. Included only for `message` items.
item.content	array	The list of message content. For audio-type content, only the transcript is returned, not the original audio data.

{
    "event_id": "event_xxx",
    "type": "conversation.item.retrieved",
    "item": {
        "id": "item_xxx",
        "object": "realtime.item",
        "type": "message",
        "role": "user",
        "content": [
            {
                "type": "input_audio",
                "transcript": "Hello"
            }
        ]
    }
}

conversation.item.input_audio_transcription.delta

Incremental ASR transcription results, streamed during speech recognition. Includes emotion and language detection information.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.input_audio_transcription.delta`.
item_id	string	The ID of the associated conversation item.
content_index	integer	The index of the content part.
text	string	The finalized transcription text.
stash	string	Provisional text that has not yet been finalized.

{
    "event_id": "event_xxx",
    "type": "conversation.item.input_audio_transcription.delta",
    "item_id": "item_xxx",
    "content_index": 0,
    "text": "Hello",
    "stash": "world"
}

conversation.item.input_audio_transcription.completed

The final ASR transcription result. The transcription text is written to the transcript field of the corresponding item.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.input_audio_transcription.completed`.
item_id	string	The ID of the associated conversation item.
content_index	integer	The index of the content part.
transcript	string	The complete transcription text.

{
    "event_id": "event_xxx",
    "type": "conversation.item.input_audio_transcription.completed",
    "item_id": "item_xxx",
    "content_index": 0,
    "transcript": "Hello world"
}

conversation.item.input_audio_transcription.failed

ASR transcription failed.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.input_audio_transcription.failed`.
item_id	string	The ID of the associated conversation item.
content_index	integer	The index of the content part.
error	object	Error details.
error.type	string	Error type, such as `transcription_error`.
error.code	string	Error code, such as `transcription_failed`.
error.message	string	Error message.

{
    "event_id": "event_xxx",
    "type": "conversation.item.input_audio_transcription.failed",
    "item_id": "item_xxx",
    "content_index": 0,
    "error": {
        "type": "transcription_error",
        "code": "transcription_failed",
        "message": "ASR transcription failed"
    }
}

conversation.item.ambient_audio_transcription.delta

smart_turn mode only. This event is not associated with any item in the conversation context.

Incremental ambient audio transcription results. When the VAD detects voice activity but semantic judgment determines the turn is not valid (for example, noise or non-semantic sounds like "um" or "uh"), the ASR result is passed through to the client as an ambient event. item_id is a separately generated, temporary ID.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.ambient_audio_transcription.delta`.
item_id	string	A separately generated, temporary ID; not associated with any item in the conversation context.
content_index	integer	The index of the content part.
text	string	The finalized transcription text.
stash	string	Provisional text that has not yet been finalized.

{
    "event_id": "event_xxx",
    "type": "conversation.item.ambient_audio_transcription.delta",
    "item_id": "item_xxx",
    "content_index": 0,
    "text": "Um",
    "stash": ""
}

conversation.item.ambient_audio_transcription.completed

smart_turn mode only. This transcription result is not written to the conversation context.

The final ambient audio transcription result. Paired with the delta event, indicating that transcription of a segment of ambient audio is complete.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `conversation.item.ambient_audio_transcription.completed`.
item_id	string	A separately generated, temporary ID; not associated with the conversation context.
content_index	integer	The index of the content part.
transcript	string	The complete transcription text.

{
    "event_id": "event_xxx",
    "type": "conversation.item.ambient_audio_transcription.completed",
    "item_id": "item_xxx",
    "content_index": 0,
    "transcript": "Um"
}

response.created

A round of model inference has started.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.created`.
response	object	The response object.
response.id	string	The unique identifier of the response.
response.object	string	Fixed as `realtime.response`.
response.status	string	The response status, such as `in_progress`.
response.modalities	array	The model's output modalities.
response.voice	string	The voice used for generated audio — either a system voice name or the `voice_id` of a voice-cloning voice.
response.output	array	The list of output items for the response; initially an empty array.

{
    "event_id": "event_xxx",
    "type": "response.created",
    "response": {
        "id": "resp_xxx",
        "object": "realtime.response",
        "status": "in_progress",
        "modalities": ["text", "audio"],
        "voice": "longanqian",
        "output": []
    }
}

response.output_item.added

A new output item was added to the response. Output items for regular replies have type message; output items for function calling have type function_call.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.output_item.added`.
response_id	string	The ID of the associated response.
output_index	integer	The index of the output item within the response.
item	object	The added output item.
item.id	string	The unique identifier of the output item.
item.object	string	Fixed as `realtime.item`.
item.type	string	The output item type: `message` (a regular message) or `function_call` (a function call).
item.status	string	The output item status, such as `in_progress`.
item.role	string	The message role, fixed as `assistant`. Included only for `message` items.
item.content	array	The list of message content. Included only for `message` items.

Example of a regular message output item:

{
    "event_id": "event_xxx",
    "type": "response.output_item.added",
    "response_id": "resp_xxx",
    "output_index": 0,
    "item": {
        "id": "item_xxx",
        "object": "realtime.item",
        "type": "message",
        "status": "in_progress",
        "role": "assistant",
        "content": []
    }
}

Example of a function call output item: When the output item is a function call, the item structure in response.output_item.added, conversation.item.created, and response.output_item.done is as follows:

{
    "id": "item_xxx",
    "object": "realtime.item",
    "type": "function_call",
    "status": "completed",
    "call_id": "call_xxx",
    "name": "get_weather",
    "arguments": "{\"city\":\"Hangzhou\"}"
}

A single response can include multiple function_call items, and may include both a regular message output and function_call outputs at the same time. Function call content is not sent to TTS for playback.

response.content_part.added

A new content part was added to an output item.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.content_part.added`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.
part	object	The added content part.
part.type	string	The content type, such as `audio` or `text`.
part.text	string	The text content; initially an empty string.

{
    "event_id": "event_xxx",
    "type": "response.content_part.added",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0,
    "part": {
        "type": "audio",
        "text": ""
    }
}

response.text.delta

Incremental text event in text-only mode, streaming text fragments.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.text.delta`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.
delta	string	The incremental text fragment.

{
    "event_id": "event_xxx",
    "type": "response.text.delta",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0,
    "delta": "Hello"
}

response.text.done

Text output complete, in text-only mode.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.text.done`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.
text	string	The complete text output.

{
    "event_id": "event_xxx",
    "type": "response.text.done",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0,
    "text": "Hello! How can I help you?"
}

response.audio_transcript.delta

Incremental caption text event in audio mode, streaming caption fragments.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.audio_transcript.delta`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.
delta	string	The incremental caption fragment.

{
    "event_id": "event_xxx",
    "type": "response.audio_transcript.delta",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0,
    "delta": "Hello"
}

response.audio_transcript.done

Caption output complete, in audio mode.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.audio_transcript.done`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.
transcript	string	The complete caption text.

{
    "event_id": "event_xxx",
    "type": "response.audio_transcript.done",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0,
    "transcript": "Hello! How can I help you?"
}

response.audio.delta

Incremental audio data event in audio mode. The delta field is Base64-encoded PCM audio data.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.audio.delta`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.
delta	string	A Base64-encoded fragment of PCM audio data.

{
    "event_id": "event_xxx",
    "type": "response.audio.delta",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0,
    "delta": "<base64-encoded audio data>"
}

response.audio.done

Audio output complete, in audio mode. Does not include audio data.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.audio.done`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.

{
    "event_id": "event_xxx",
    "type": "response.audio.done",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0
}

response.content_part.done

A content part within an output item has finished being output.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.content_part.done`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
content_index	integer	The index of the content part within the output item.
part	object	The completed content part.
part.type	string	The content type, such as `audio` or `text`.
part.text	string	The text content or audio caption text.

{
    "event_id": "event_xxx",
    "type": "response.content_part.done",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "content_index": 0,
    "part": {
        "type": "audio",
        "text": "Hello! How can I help you?"
    }
}

response.output_item.done

An output item within the response has finished being output.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.output_item.done`.
response_id	string	The ID of the associated response.
output_index	integer	The index of the output item within the response.
item	object	The complete finished output item.
item.id	string	The unique identifier of the output item.
item.object	string	Fixed as `realtime.item`.
item.type	string	The output item type: `message` (a regular message) or `function_call` (a function call).
item.status	string	The output item status, such as `completed`.
item.role	string	The message role, fixed as `assistant`. Included only for `message` items.
item.content	array	The list of message content. Included only for `message` items.

{
    "event_id": "event_xxx",
    "type": "response.output_item.done",
    "response_id": "resp_xxx",
    "output_index": 0,
    "item": {
        "id": "item_xxx",
        "object": "realtime.item",
        "type": "message",
        "status": "completed",
        "role": "assistant",
        "content": [
            {
                "type": "text",
                "text": "Hello! How can I help you?"
            }
        ]
    }
}

response.function_call_arguments.delta

Incremental function calling arguments. When the model decides to call a tool, the server first sends response.output_item.added (with item.type=function_call) and the corresponding conversation.item.created, then streams the argument fragments via this event.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.function_call_arguments.delta`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
call_id	string	The unique identifier of the function call.
delta	string	An incremental fragment of the function call arguments (a JSON string fragment).

{
    "event_id": "event_xxx",
    "type": "response.function_call_arguments.delta",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "call_id": "call_xxx",
    "delta": "{\"city"
}

response.function_call_arguments.done

Function calling arguments output complete. After receiving this event, the client should execute the corresponding tool, write back a function_call_output via conversation.item.create, and then send response.create to trigger the second round of inference.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.function_call_arguments.done`.
response_id	string	The ID of the associated response.
item_id	string	The ID of the associated output item.
output_index	integer	The index of the output item within the response.
call_id	string	The unique identifier of the function call.
name	string	The name of the called function.
arguments	string	The complete function call arguments (a JSON string).

{
    "event_id": "event_xxx",
    "type": "response.function_call_arguments.done",
    "response_id": "resp_xxx",
    "item_id": "item_xxx",
    "output_index": 0,
    "call_id": "call_xxx",
    "name": "get_weather",
    "arguments": "{\"city\":\"Hangzhou\"}"
}

response.done

A round of inference is complete. status indicates the reason for completion.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `response.done`.
response	object	The complete response object.
response.id	string	The unique identifier of the response.
response.object	string	Fixed as `realtime.response`.
response.status	string	The final status of the response: `completed` (finished normally), `cancelled` (interrupted and cancelled), or `failed` (LLM or TTS error).
response.status_details	object	Status details, present only when `cancelled` or `failed`.
response.status_details.type	string	The status type, such as `cancelled`.
response.status_details.reason	string	The cancellation reason: `turn_detected` (interrupted by VAD) or `client_cancelled` (cancelled by the client).
response.modalities	array	The model's output modalities.
response.voice	string	The voice used for generated audio — either a system voice name or the `voice_id` of a voice-cloning voice.
response.output	array	The list of output items for the response, containing the complete item objects.

Completed normally
Interrupted

{
    "event_id": "event_xxx",
    "type": "response.done",
    "response": {
        "id": "resp_xxx",
        "object": "realtime.response",
        "status": "completed",
        "modalities": ["text", "audio"],
        "voice": "longanqian",
        "output": [
            {
                "id": "item_xxx",
                "object": "realtime.item",
                "type": "message",
                "status": "completed",
                "role": "assistant",
                "content": [
                    {
                        "type": "audio",
                        "transcript": "Hello! How can I help you?"
                    }
                ]
            }
        ]
    }
}

{
    "event_id": "event_xxx",
    "type": "response.done",
    "response": {
        "id": "resp_xxx",
        "status": "cancelled",
        "status_details": {
            "type": "cancelled",
            "reason": "turn_detected"
        }
    }
}

voiceprint_audio_list.in_progress

Voiceprint enrollment is proceeding asynchronously.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `voiceprint_audio_list.in_progress`.
item_id	string	The unique identifier of the voiceprint enrollment task.

{
    "event_id": "event_PaEcN7CCrlhE8q4MM2yND",
    "type": "voiceprint_audio_list.in_progress",
    "item_id": "vp_Y12cA986j1KZ9O9YmAXOA"
}

voiceprint_audio_list.completed

Voiceprint enrollment is complete.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `voiceprint_audio_list.completed`.
item_id	string	The unique identifier of the voiceprint enrollment task.

{
    "event_id": "event_PaEcN7CCrlhE8q4MM2yND",
    "type": "voiceprint_audio_list.completed",
    "item_id": "vp_Y12cA986j1KZ9O9YmAXOA"
}

voiceprint_audio_list.failed

Voiceprint enrollment failed. This does not block normal conversation calls.

Field	Type	Description
event_id	string	The unique identifier of this event.
type	string	Event type, fixed as `voiceprint_audio_list.failed`.
item_id	string	The unique identifier of the voiceprint enrollment task.
reason	string	A description of the failure reason.

{
    "event_id": "event_PaEcN7CCrlhE8q4MM2yND",
    "type": "voiceprint_audio_list.failed",
    "item_id": "vp_Y12cA986j1KZ9O9YmAXOA",
    "reason": ""
}

​error

​session.created

​session.updated

​input_audio_buffer.speech_started

​input_audio_buffer.speech_stopped

​input_audio_buffer.committed

​input_audio_buffer.cleared

​conversation.item.created

​conversation.item.deleted

​conversation.item.retrieved

​conversation.item.input_audio_transcription.delta

​conversation.item.input_audio_transcription.completed

​conversation.item.input_audio_transcription.failed

​conversation.item.ambient_audio_transcription.delta

​conversation.item.ambient_audio_transcription.completed

​response.created

​response.output_item.added

​response.content_part.added

​response.text.delta

​response.text.done

​response.audio_transcript.delta

​response.audio_transcript.done

​response.audio.delta

​response.audio.done

​response.content_part.done

​response.output_item.done

​response.function_call_arguments.delta

​response.function_call_arguments.done

​response.done

​voiceprint_audio_list.in_progress

​voiceprint_audio_list.completed

​voiceprint_audio_list.failed

error

session.created

session.updated

input_audio_buffer.speech_started

input_audio_buffer.speech_stopped

input_audio_buffer.committed

input_audio_buffer.cleared

conversation.item.created

conversation.item.deleted

conversation.item.retrieved

conversation.item.input_audio_transcription.delta

conversation.item.input_audio_transcription.completed

conversation.item.input_audio_transcription.failed

conversation.item.ambient_audio_transcription.delta

conversation.item.ambient_audio_transcription.completed

response.created

response.output_item.added

response.content_part.added

response.text.delta

response.text.done

response.audio_transcript.delta

response.audio_transcript.done

response.audio.delta

response.audio.done

response.content_part.done

response.output_item.done

response.function_call_arguments.delta

response.function_call_arguments.done

response.done

voiceprint_audio_list.in_progress

voiceprint_audio_list.completed

voiceprint_audio_list.failed