Realtime API Server-Side Events (Qwen-Omni-Realtime) - Alibaba Cloud Model Studio

Server events for the Qwen-Omni-Realtime API, including tool calling (function calling) events.

NoteThis page is the event reference for Qwen-Omni-Realtime. Event definitions are based on WebSocket access. AOQ and WebRTC use their respective data channels to send and receive model events, and media tracks to transmit media. First read WebSocket access, WebRTC access, or AOQ access.

For WebSocket SDK usage, see Python SDK and Java SDK. To select a model and protocol, see Overview.

error

Server error.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always error.

errorobject

Error details.

Properties

typestring

The error type.

codestring

The error code.

messagestring

The error message.

paramstring

The parameter associated with the error, such as session.modalities.

{
  "event_id": "event_RoUu4T8yExPMI37GKwaOC",
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "code": "invalid_value",
    "message": "Invalid modalities: ['audio']. Supported combinations are: ['text'] and ['audio', 'text'].",
    "param": "session.modalities"
  }
}

session.created

Returned when a client connects. Contains the default session configuration.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always session.created.

sessionobject

The session configuration.

Properties

objectstring

This value is always realtime.session.

modelstring

The model used.

modalitiesarray

The output modalities for the model.

voicestring

The voice for model-generated audio.

input_audio_formatstring

Input audio format. Only pcm is supported (16 kHz sample rate).

output_audio_formatstring

Output audio format. Only pcm is supported (24 kHz sample rate).

input_audio_transcriptionobject

The transcription configuration.

Properties

modelstring

Transcription model. Always qwen3-asr-flash-realtime. Not configurable.

turn_detectionobject

The voice activity detection (VAD) configuration.

Properties

typestring

The VAD type. Valid values are server_vad (default), semantic_vad, or semantic_vad_ec. The semantic_vad_ec mode is supported by the Qwen3.8-Omni-Flash-Realtime series. See Client events.

thresholdfloat

The VAD detection threshold.

silence_duration_msinteger

Silence duration (ms) that triggers end-of-speech detection.

idle_timeout_msinteger

The idle timeout in milliseconds. Returned only in server_vad mode with qwen3.5-omni-plus-realtime or qwen3.5-omni-flash-realtime models.

enable_searchboolean

Whether to enable web search. Supported by Qwen3.8-Omni-Flash-Realtime and Qwen3.5-Omni-Realtime models.

search_optionsobject

The options for the web search.

temperaturefloat

The temperature parameter for the model.

The following example is the default session returned by qwen3.8-omni-flash-realtime in the Beijing region.

{
    "event_id": "event_QQubXbhHMyXmKaSuE6PQ8",
    "type": "session.created",
    "session": {
        "input_audio_format": "pcm",
        "input_audio_transcription": {
            "model": "qwen3-asr-flash-realtime"
        },
        "id": "sess_MjEctgJ4ziXPEioCzSSvK",
        "object": "realtime.session",
        "modalities": [
            "text",
            "audio"
        ],
        "turn_detection": {
            "type": "server_vad",
            "silence_duration_ms": 800,
            "interrupt_response": true,
            "create_response": true,
            "threshold": 0.5,
            "prefix_padding_ms": 300
        },
        "model": "qwen3.8-omni-flash-realtime",
        "voice": "Tina",
        "output_audio_format": "pcm"
    }
}

session.updated

Returned after a successful session.update request. On failure, an error event is returned instead.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always session.updated.

sessionobject

The session configuration.

Properties

temperaturefloat

The temperature parameter for the model.

modalitiesarray

The output modalities for the model.

voicestring

The voice for model-generated audio.

instructionsstring

The model's goal and role.

input_audio_formatstring

Input audio format. Only pcm is supported (16 kHz sample rate).

output_audio_formatstring

Output audio format. Only pcm is supported (24 kHz sample rate).

input_audio_transcriptionobject

The transcription configuration.

Properties

modelstring

Transcription model. Always qwen3-asr-flash-realtime. Not configurable.

turn_detectionobject

The voice activity detection (VAD) configuration.

Properties

typestring

The VAD type. Valid values are server_vad (default), semantic_vad, or semantic_vad_ec. The semantic_vad_ec mode is supported by the Qwen3.8-Omni-Flash-Realtime series. See Client events.

thresholdfloat

The VAD detection threshold.

silence_duration_msinteger

Silence duration (ms) that triggers end-of-speech detection.

idle_timeout_msinteger

The idle timeout in milliseconds. Returned only in server_vad mode with qwen3.5-omni-plus-realtime or qwen3.5-omni-flash-realtime models.

enable_searchboolean(optional)

Whether to enable web search. Supported by Qwen3.8-Omni-Flash-Realtime and Qwen3.5-Omni-Realtime models.

search_optionsobject(optional)

The web search options.

toolsarray(optional)

Tool definitions. The properties below describe Function Calling tools with type="function". See client tool configuration for Qwen3.8-Omni-Flash-Realtime MCP fields; MCP endpoints and credentials are not echoed in session.updated.

Properties

typestring(required)

This value is always function.

functionobject

Properties

namestring(required)

The function name, such as get_current_weather or get_current_time.

descriptionstring(optional)

Description of the function's purpose. The model uses this to decide whether to call the function.

parametersobject(optional)

Input parameter schema. The model uses this to extract parameters. Omit if the function takes no parameters.

Properties

typestring(required)

This value is always object.

propertiesobject(optional)

Each key is a parameter name mapped to an object with type and description.

requiredarray(optional)

Specifies which input parameters are required.

top_pfloat

The probability threshold for nucleus sampling.

top_kinteger

Candidate set size for sampling during generation.

max_tokensinteger

Maximum tokens the model can return for this request.

repetition_penaltyfloat

Controls repetition in consecutive sequences during generation.

presence_penaltyfloat

Controls repetition in generated content.

seedinteger

The degree of consistency in the model's output per request.

The following example uses qwen3.8-omni-flash-realtime in the Beijing region, with text-only output and max_tokens=32.

{
    "event_id": "event_TSBGI9Yj5ecCKjiGO34VB",
    "type": "session.updated",
    "session": {
        "id": "sess_MjEctgJ4ziXPEioCzSSvK",
        "object": "realtime.session",
        "model": "qwen3.8-omni-flash-realtime",
        "modalities": [
            "text"
        ],
        "instructions": "请只回复 OK。",
        "voice": "Tina",
        "input_audio_format": "pcm",
        "output_audio_format": "pcm",
        "input_audio_transcription": {
            "model": "qwen3-asr-flash-realtime"
        },
        "max_tokens": 32
    }
}

input_audio_buffer.speech_started

In VAD mode, returned when the server detects speech onset in the audio buffer.

May be triggered each time audio is added to the buffer before speech is detected.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always input_audio_buffer.speech_started.

audio_start_msinteger

Time (ms) from when audio buffer writing starts until speech is first detected.

item_idstring

ID of the user message item created when end-of-speech is detected.

User message items append user input to the conversation history for model inference.

{
    "event_id": "event_Pvp8nEhsQuGCQbFJ9x58n",
    "type": "input_audio_buffer.speech_started",
    "audio_start_ms": 3647,
    "item_id": "item_YbAiGvK2H7YaS34o4R6Ba"
}

input_audio_buffer.speech_stopped

In VAD mode, returned when the server detects end-of-speech in the audio buffer.

Also returns a conversation.item.created event with the corresponding user message item.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always input_audio_buffer.speech_stopped.

audio_end_msinteger

Time (ms) from session start until end-of-speech is detected.

item_idstring

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

{
    "event_id": "event_UhQiqNVRsgUiq4KUS5Xb5",
    "type": "input_audio_buffer.speech_stopped",
    "audio_end_ms": 4453,
    "item_id": "item_YbAiGvK2H7YaS34o4R6Ba"
}

input_audio_buffer.committed

Returned when the input audio buffer is committed.

In VAD mode, the server automatically commits the buffer when it detects end-of-speech.
In Manual mode, returned after the client sends an input_audio_buffer.commit event.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always input_audio_buffer.committed.

item_idstring

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

{
    "event_id": "event_Iy6sUzL1nmdFgshFYxJEz",
    "type": "input_audio_buffer.committed",
    "item_id": "item_YbAiGvK2H7YaS34o4R6Ba"
}

input_audio_buffer.cleared

Returned after the client sends an input_audio_buffer.clear event.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always input_audio_buffer.cleared.

{
  "event_id": "event_RoUu4T8yExPMI37GKwaOC",
  "type": "input_audio_buffer.cleared"
}

conversation.item.created

Returned when a conversation item is created.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always conversation.item.created.

response_idstring(conditionally required)

Returned only when item.type is mcp_approval_request; identifies the parent Response that generated the MCP call.

item_idstring(conditionally required)

Returned only when item.type is mcp_approval_request; the approval item ID, equal to item.id.

previous_item_idstring(conditionally required)

Returned only when item.type is mcp_approval_request; identifies the mcp_call item under review.

itemobject

The conversation item to add.

Properties

idstring

The unique ID of the conversation item.

objectstring

For message and function_call items, this field is realtime.item. For MCP items, it has the same value when returned.

statusstring

When returned, this field indicates the conversation item status. An initial mcp_call item requires it with the value in_progress.

rolestring

Present only on message items; identifies the message role.

contentarray of objects

The content of the message, returned when the type is message. The following fields describe the array element in this example.

Array item

typestring

The content-part type; input_audio in this example.

typestring

The conversation item type includes message and function_call. Qwen3.8-Omni-Flash-Realtime also returns mcp_list_tools, mcp_call, and mcp_approval_request; see MCP item examples.

namestring

The name of the function that is called when the type is function_call.

call_idstring

When the type is function_call, this is the unique ID of the function invocation.

argumentsstring

When the type is function_call, this parameter contains the arguments for the function invocation as a JSON string.

type=mcp_list_tools

For this item type, item.id matches the item_id in tool discovery status events.

server_labelstring(required)

Identifies the MCP server.

toolsarray of objects(required)

Validated tool definitions after allowed_tools filtering; empty if discovery fails.

Array item

namestring(required)

Original tool name, 1–64 characters using letters, digits, underscores, periods, or hyphens.

descriptionstring(optional)

Tool description from the MCP server.

input_schemaobject(required)

JSON Schema from the MCP server. The service does not perform full JSON Schema semantic validation; the MCP server ultimately validates arguments.

Properties

typestring(required)

The root value must be object.

propertiesobject(optional)

List each parameter under its custom name. For example, city in the mcp_list_tools example is a parameter name; its type and description describe the data type and purpose. The MCP server defines each parameter's JSON Schema.

requiredarray of strings(optional)

Names of required parameters.

Other standard JSON Schema fields, including additionalProperties, $defs, oneOf, anyOf, and allOf, pass through from the original schema.

annotationsobject(optional)

ToolAnnotations from the MCP server. The following MCP standard hint fields are optional; the server determines which fields it returns.

Properties

titlestring(optional)

Display name of the tool.

readOnlyHintboolean(optional)

Hints whether the tool is read-only.

destructiveHintboolean(optional)

Hints whether the tool may make destructive changes.

idempotentHintboolean(optional)

Hints whether repeated calls have no additional effect.

openWorldHintboolean(optional)

Hints whether the tool may interact with external systems. These fields are hints and must not be used as a security guarantee.

errorobject(optional)

Returned on discovery failure.

Properties

typestring(required)

Must be tool_execution_error.

messagestring(required)

A client-safe description without sensitive upstream response content.

type=mcp_call (initial item)

objectstring(required)

Must be realtime.item.

statusstring(required)

Initially in_progress.

server_labelstring(required)

Identifies the MCP server executing the tool.

namestring(required)

Original tool name.

call_idstring(required)

Unique ID of this call.

argumentsstring(required)

Usually empty initially; use later events and the final item for full arguments.

type=mcp_approval_request

Copy this approval item's item.id unchanged into approval_request_id when replying.

server_labelstring(required)

Identifies the MCP server for the pending tool.

namestring(required)

Original name of the pending tool.

argumentsstring(required)

Full JSON string of arguments awaiting approval.

call_idstring(required)

ID of the call awaiting approval.

Example:

{
    "event_id": "event_JEfkrr9gO3Ny7Xcv9bGVd",
    "type": "conversation.item.created",
    "item": {
        "id": "item_YbAiGvK2H7YaS34o4R6Ba",
        "object": "realtime.item",
        "type": "message",
        "status": "in_progress",
        "role": "assistant",
        "content": [
            {
                "type": "input_audio"
            }
        ]
    }
}
// Tool calling scenario
{
    "event_id": "event_S1hkaIQgcuQD8OEdOpGHQ",
    "type": "conversation.item.created",
    "item": {
        "id": "item_FEG9qJGNkPcdf4et3p7BV",
        "object": "realtime.item",
        "type": "function_call",
        "status": "in_progress",
        "call_id": "call_bc0a7fb7235840f69ecfe4",
        "name": "get_current_weather",
        "arguments": ""
    }
}

conversation.item.input_audio_transcription.delta

Sent frequently while the user is speaking when input audio transcription is enabled. Provides real-time intermediate transcription results. Concatenate text + stash for the most complete sentence preview at any point.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always conversation.item.input_audio_transcription.delta.

item_idstring

The ID of the associated conversation item.

content_indexinteger

The index of the content part that contains the audio.

textstring

Confirmed text prefix — the portion the model has finalized and will not change.

stashstring

Preliminary text suffix — a temporary draft following the confirmed portion, subject to revision.

languagestring

The detected language of the recognized audio.

emotionstring

The detected emotion of the recognized audio. Valid values: neutral, happy, sad, angry, surprised, disgusted, fearful.

{
    "event_id": "event_C7jzoeSFuiwOZS6tR14yx",
    "type": "conversation.item.input_audio_transcription.delta",
    "item_id": "item_ThVYhLHOdeXb4bBSvzSFF",
    "content_index": 0,
    "text": "",
    "stash": "How is the weather today?",
    "language": "en",
    "emotion": "neutral",
    "obfuscation": "ABEXGYmxdmc97u"
}

To get the most complete sentence preview at any moment, concatenate these two fields: real-time preview = text + stash.

Click to view example

Suppose the user is saying: "The weather is nice today, sunny and warm."

The following shows the event stream you might receive and how to interpret them:

Time	User speech progress	API response (text and stash)	Client UI display (text + stash)
T1	"The weather..."	text: "" stash: "The weather"	The weather
T2	"...is nice..."	text: "" stash: "The weather is nice"	The weather is nice
T3	"...today,"	text: "The weather" stash: " is nice today,"	The weather is nice today, ("The weather" has been confirmed and moved to text)
T4	(brief pause)	text: "The weather is nice today, " stash: ""	The weather is nice today, (first clause fully confirmed)
T5	"sunny..."	text: "The weather is nice today, " stash: "sunny"	The weather is nice today, sunny
T6	"...and warm."	text: "The weather is nice today, " stash: "sunny and warm."	The weather is nice today, sunny and warm.
T7	(stops speaking)	-	Use the transcript from conversation.item.input_audio_transcription.completed as the final result.

conversation.item.input_audio_transcription.completed

Indicates that the user's audio has been transcribed by the built-in speech recognition model (qwen3-asr-flash-realtime). Not configurable.

The transcribed text from the speech recognition model may differ from the interpretation generated by the Qwen-Omni-Realtime model. The transcription is for reference only.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always conversation.item.input_audio_transcription.completed.

item_idstring

The ID of the user message item.

content_indexinteger

This value is always 0.

transcriptstring

The transcribed text.

{
    "event_id": "event_FrrZcxiDfTB9LD9p4pVng",
    "type": "conversation.item.input_audio_transcription.completed",
    "item_id": "item_YbAiGvK2H7YaS34o4R6Ba",
    "content_index": 0,
    "transcript": "Hello."
}

conversation.item.input_audio_transcription.failed

Returned when input audio transcription is enabled and the transcription fails. Independent of the error event; helps clients identify transcription failures specifically.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always conversation.item.input_audio_transcription.failed.

item_idstring

The ID of the user message item.

content_indexinteger

This value is always 0.

errorobject

The error information.

Properties

codestring

The error code.

messagestring

The error message.

paramstring

The parameter related to the error.

{
  "type": "conversation.item.input_audio_transcription.failed",
  "item_id": "<item_id>",
  "content_index": 0,
  "error": {
    "code": "<code>",
    "message": "<message>",
    "param": "<param>"
  }
}

response.created

Returned when the server starts generating a new response.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.created.

responseobject

The response object.

Properties

idstring

The unique ID of the response.

conversation_idstring

The unique ID of the current session.

objectstring

The object type. For this event, this value is always realtime.response.

statusstring

The response status. Valid values are completed, failed, in_progress, or incomplete.

modalitiesarray

The response modalities.

voicestring

The voice for model-generated audio.

outputarray

This field is empty for this event.

{
    "event_id": "event_XuDavMzQN3KKepqGu3KRh",
    "type": "response.created",
    "response": {
        "id": "resp_HaVOPdbmX6vifiV5pAfJY",
        "object": "realtime.response",
        "conversation_id": "conv_FjJaccpnvwHNo9cPVuzGc",
        "status": "in_progress",
        "modalities": [
            "text",
            "audio"
        ],
        "voice": "Cherry",
        "output_audio_format": "pcm",
        "output": []
    }
}

response.done

Returned after the response is fully generated. The response object includes all output items except raw audio data.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.done.

responseobject

The response object.

Properties

idstring

The unique ID of the response.

conversation_idstring

The unique ID of the current session.

objectstring

The object type. For this event, this value is always realtime.response.

statusstring

The response status.

modalitiesarray

The response modalities.

voicestring

The voice for model-generated audio.

outputarray

The response output items. Each array element is a conversation item object.

Array item

idstring

The ID of the response output.

typestring

The type of the output item. Values include message and function_call. Qwen3.8-Omni-Flash-Realtime also supports mcp_call; see MCP item examples.

objectstring

For message and function_call items, this field is realtime.item. For MCP items, it has the same value when returned.

statusstring

The output item status.

rolestring

Present only on message items; identifies the message role.

contentarray

The output item content, returned only when type is message. Each array element is a content-part object.

Array item

typestring

The content type. The value can be text for plain text output or audio for audio output.

textstring

The text output.

transcriptstring

The text transcript of the audio.

namestring

The name of the function that is invoked when the type is function_call.

call_idstring

When the type is function_call, this is the unique ID of the function invocation.

argumentsstring

When the type is function_call, this field contains the full arguments for the function call as a JSON string.

type=mcp_call (final item)

statusstring(required)

completed or failed.

server_labelstring(required)

Identifies the MCP server that executed the tool.

namestring(required)

Original tool name.

call_idstring(required)

Unique ID of this call.

argumentsstring(required)

Full JSON string of arguments.

outputstring(optional)

A JSON string serialized from MCP tools/call.result. It may also appear in some failure cases.

errorobject(optional)

Returned on failure.

Properties

typestring(required)

Must be tool_execution_error.

messagestring(required)

A client-safe description without sensitive upstream response content.

If the MCP server returns isError=true, the final status is failed and the original output may also be present.

usageobject

Token usage details for this response.

Properties

total_tokensinteger

Total tokens used in this response.

input_tokensinteger

Number of input tokens.

output_tokensinteger

Number of output tokens.

input_tokens_detailsobject

Details about input token usage, including text_tokens and audio_tokens.

output_tokens_detailsobject

Details about output token usage, including text_tokens and audio_tokens.

pluginsobject(optional)

Plugin usage metrics. Returned when web search (enable_search) is enabled.

Properties

searchobject

Search metering data.

Properties

countinteger

The number of searches.

strategystring

The search strategy.

Example:

{
    "event_id": "event_CSaxRRYLvbrfexDXAEuDG",
    "type": "response.done",
    "response": {
        "id": "resp_HaVOPdbmX6vifiV5pAfJY",
        "object": "realtime.response",
        "conversation_id": "conv_FjJaccpnvwHNo9cPVuzGc",
        "status": "completed",
        "modalities": [
            "text",
            "audio"
        ],
        "voice": "Cherry",
        "output_audio_format": "pcm",
        "output": [
            {
                "id": "item_Ls6MtCUWO7LM4E59QziNv",
                "object": "realtime.item",
                "type": "message",
                "status": "completed",
                "role": "assistant",
                "content": [
                    {
                        "type": "audio",
                        "transcript": "Hello! How can I help you?"
                    }
                ]
            }
        ],
        "usage": {
            "total_tokens": 377,
            "input_tokens": 336,
            "output_tokens": 41,
            "input_tokens_details": {
                "text_tokens": 228,
                "audio_tokens": 108
            },
            "output_tokens_details": {
                "text_tokens": 9,
                "audio_tokens": 32
            },
            "plugins": {
                "search": {
                    "count": 1,
                    "strategy": "agent"
                }
            }
        }
    }
}
// Tool calling scenario
{
    "event_id": "event_T1EFAJp43X2DWtDRmxTtx",
    "type": "response.done",
    "response": {
        "id": "resp_TucN5QgymL5MA8vkJvFlS",
        "object": "realtime.response",
        "conversation_id": "conv_SEDZESRlefT8WvLSmEn6E",
        "status": "completed",
        "modalities": ["text", "audio"],
        "voice": "Ethan",
        "output_audio_format": "pcm",
        "output": [
            {
                "id": "item_FEG9qJGNkPcdf4et3p7BV",
                "object": "realtime.item",
                "type": "function_call",
                "status": "completed",
                "call_id": "call_bc0a7fb7235840f69ecfe4",
                "name": "get_current_weather",
                "arguments": " {\"location\": \"Hangzhou\"}"
            }
        ],
        "usage": {
            "total_tokens": 567,
            "input_tokens": 524,
            "output_tokens": 43,
            "input_tokens_details": {
                "text_tokens": 487,
                "audio_tokens": 37
            },
            "output_tokens_details": {
                "text_tokens": 43
            }
        }
    }
}

response.text.delta

Returned when the output modality is text-only and the model generates new text incrementally.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.text.delta.

deltastring

Incremental text generated by the model.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response. This value is always 0.

content_indexinteger

The index of the internal part within the output item. This value is always 0.

{
    "delta": "Hello",
    "event_id": "event_TH49MauuPmRo1RGaMSlP7",
    "type": "response.text.delta",
    "response_id": "resp_PrRSvPVpnCExdUOGHHLuP",
    "item_id": "item_L8IRm9kRXFpxoOjDqDC96",
    "output_index": 0,
    "content_index": 0
}

response.text.done

Returned when the output modality is text-only and the model finishes generating text.

Also returned if the response is interrupted, incomplete, or canceled.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.text.done.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response.

content_indexinteger

The index of the output item in the response.

textstring

The full text generated by the model.

{
  "event_id": "event_B1lIeE2Nac33zn5V7h2mm",
  "type": "response.text.done",
  "response_id": "resp_B1lIdtjF4Noqpn5NOjznj",
  "item_id": "item_B1lIdJsAJlJiFs8ztWpJt",
  "output_index": 0,
  "content_index": 0,
  "text": "How can I assist you today?"
}

response.audio.delta

For WebSocket access, the server returns this event when the output modalities include audio and the model incrementally generates new audio data. For WebRTC access, audio is transmitted over RTP audio tracks, and this event is not returned.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.audio.delta.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response.

content_indexinteger

The index of the output item in the response.

deltastring

Incremental audio data, Base64-encoded.

{
  "event_id": "event_B1osWMZBtrEQbiIwW0qHQ",
  "type": "response.audio.delta",
  "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
  "item_id": "item_OFaPGtzfWCPyGzxnuEX9i",
  "output_index": 0,
  "content_index": 0,
  "delta": "{base64 audio}"
}

response.audio.done

Returned when the output modality includes audio and the model finishes generating audio data.

Also returned if the response is interrupted, incomplete, or canceled.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.audio.done.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response.

content_indexinteger

The index of the output item in the response.

{
    "event_id": "event_Le1TDl7VfyHQxl47DtGxI",
    "type": "response.audio.done",
    "response_id": "resp_HaVOPdbmX6vifiV5pAfJY",
    "item_id": "item_Ls6MtCUWO7LM4E59QziNv",
    "output_index": 0,
    "content_index": 0
}

response.audio_transcript.delta

Returned when the output modality includes audio and the model generates new response.audio_transcript.delta transcript text incrementally.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.audio_transcript.delta.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response.

content_indexinteger

The index of the output item in the response.

deltastring

The incremental text.

{
    "event_id": "event_BksW7fOwnyavZdDxIzZYM",
    "type": "response.audio_transcript.delta",
    "response_id": "resp_HaVOPdbmX6vifiV5pAfJY",
    "item_id": "item_Ls6MtCUWO7LM4E59QziNv",
    "output_index": 0,
    "content_index": 0,
    "delta": "What"
}

response.audio_transcript.done

Returned as a response.audio_transcript.done event when the output modality includes audio and the model completes the audio transcript.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.audio_transcript.done.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response.

content_indexinteger

The index of the output item in the response.

transcriptstring

The full transcription text.

{
    "event_id": "event_X49tL2WerT4WjxcmH16lS",
    "type": "response.audio_transcript.done",
    "response_id": "resp_HaVOPdbmX6vifiV5pAfJY",
    "item_id": "item_Ls6MtCUWO7LM4E59QziNv",
    "output_index": 0,
    "content_index": 0,
    "transcript": "Hello! How can I help you?"
}

response.function_call_arguments.delta

Returned as the model streams function call arguments. Concatenate the delta fields in order to build the argument string. The complete content is provided in the subsequent response.function_call_arguments.done event.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.function_call_arguments.delta.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response.

call_idstring

The unique ID for this function invocation. This is consistent with the done event in the same turn.

deltastring

New segment of the argument string. Concatenate segments in order.

{
    "event_id": "event_SlKoJyEbPEqLq14DSM1u5",
    "type": "response.function_call_arguments.delta",
    "response_id": "resp_JnTOsWXlFhKcFohZbtfz6",
    "item_id": "item_Rhcms7CauTNsQprV5S4Hr",
    "output_index": 0,
    "call_id": "call_2be200f4cafe419b9530dd",
    "delta": " {\"location\": \"Beijing\"}"
}

response.function_call_arguments.done

Indicates that function call arguments are fully generated. The arguments field contains the complete argument string. Use the arguments from this event — not the concatenated delta results — to parse and call the local function.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.function_call_arguments.done.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response.

call_idstring

The unique ID for this function invocation.

namestring

The name of the function that was called.

argumentsstring

Complete function call arguments as a JSON string.

{
    "event_id": "event_X6suLyuL5agdH7r6koesM",
    "type": "response.function_call_arguments.done",
    "response_id": "resp_JnTOsWXlFhKcFohZbtfz6",
    "item_id": "item_Rhcms7CauTNsQprV5S4Hr",
    "output_index": 0,
    "name": "get_current_weather",
    "call_id": "call_2be200f4cafe419b9530dd",
    "arguments": " {\"location\": \"Beijing\"}"
}

response.output_item.added

Returned when a new item is created during response generation. The item type can be message or function_call; Qwen3.8-Omni-Flash-Realtime also supports mcp_call; see MCP item examples.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.output_item.added.

response_idstring

The response ID.

output_indexinteger

The index of the output item in the response.

itemobject

Information about the output item.

Properties

idstring

The unique ID of the output item.

objectstring

For message and function_call items, this field is realtime.item. For MCP items, it has the same value when returned.

statusstring

The status of the output item.

rolestring

Present only on message items; identifies the message role.

contentarray

The content of the message, returned when the type is message. The array is initially empty in this example; see the completed item in the response.output_item.done example.

typestring

The type of the output item. Values include message and function_call. Qwen3.8-Omni-Flash-Realtime also supports mcp_call; see MCP item examples.

namestring

The name of the function to call when the type is function_call.

call_idstring

The unique ID of the current function invocation when the type is function_call.

argumentsstring

Function call arguments as a JSON string when the type is function_call. Initially an empty string in added events.

type=mcp_call (initial item)

objectstring(required)

Must be realtime.item.

statusstring(required)

Initially in_progress.

server_labelstring(required)

Identifies the MCP server executing the tool.

namestring(required)

Original tool name.

call_idstring(required)

Unique ID of this call.

argumentsstring(required)

Usually empty initially; use response.mcp_call_arguments.done and the final item for full arguments.

{
    "event_id": "event_DsCO341DEVtiATtCB6BUY",
    "type": "response.output_item.added",
    "response_id": "resp_HaVOPdbmX6vifiV5pAfJY",
    "output_index": 0,
    "item": {
        "id": "item_Ls6MtCUWO7LM4E59QziNv",
        "object": "realtime.item",
        "type": "message",
        "status": "in_progress",
        "role": "assistant",
        "content": []
    }
}
// Tool calling scenario
{
    "event_id": "event_HXmKt5pGoiRtXx7Hq7zpN",
    "type": "response.output_item.added",
    "response_id": "resp_TucN5QgymL5MA8vkJvFlS",
    "output_index": 0,
    "item": {
        "id": "item_FEG9qJGNkPcdf4et3p7BV",
        "object": "realtime.item",
        "type": "function_call",
        "status": "in_progress",
        "call_id": "call_bc0a7fb7235840f69ecfe4",
        "name": "get_current_weather",
        "arguments": ""
    }
}

response.output_item.done

Returned when an output item is fully generated.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.output_item.done.

response_idstring

The response ID.

output_indexinteger

The index of the output item in the response.

itemobject

The output item information.

Properties

idstring

The unique ID of the output item.

objectstring

For message and function_call items, this field is realtime.item. For MCP items, it has the same value when returned.

statusstring

The status of the output item.

rolestring

Present only on message items; identifies the message role.

contentarray of objects

The content of the message, returned when the type is message. The following fields describe the array element in this example.

Array item

typestring

The content-part type; audio in this example.

textstring

Text content in this example.

typestring

The type of the output item. Values include message and function_call. Qwen3.8-Omni-Flash-Realtime also supports mcp_call; see MCP item examples.

namestring

The name of the function that is called when the type is function_call.

call_idstring

When the type is function_call, this is the unique ID for the function invocation.

argumentsstring

When the type is function_call, contains the full function call arguments as a JSON string.

type=mcp_call (final item)

statusstring(required)

completed or failed.

server_labelstring(required)

Identifies the MCP server that executed the tool.

namestring(required)

Original tool name.

call_idstring(required)

Unique ID of this call.

argumentsstring(required)

Full JSON string of arguments.

outputstring(optional)

A JSON string serialized from MCP tools/call.result. It may also appear in some failure cases.

errorobject(optional)

Returned on failure.

Properties

typestring(required)

Must be tool_execution_error.

messagestring(required)

A client-safe description without sensitive upstream response content.

If the MCP server returns isError=true, the final status is failed and the original output may also be present.

{
    "event_id": "event_MEu5nlLw1LsOguHiehIP8",
    "type": "response.output_item.done",
    "response_id": "resp_HaVOPdbmX6vifiV5pAfJY",
    "output_index": 0,
    "item": {
        "id": "item_Ls6MtCUWO7LM4E59QziNv",
        "object": "realtime.item",
        "type": "message",
        "status": "completed",
        "role": "assistant",
        "content": [
            {
                "type": "audio",
                "text": "Hello! How can I help you?"
            }
        ]
    }
}
// Tool calling scenario
{
    "event_id": "event_FHspdfAnCyjuME3mmAwSY",
    "type": "response.output_item.done",
    "response_id": "resp_TucN5QgymL5MA8vkJvFlS",
    "output_index": 0,
    "item": {
        "id": "item_FEG9qJGNkPcdf4et3p7BV",
        "object": "realtime.item",
        "type": "function_call",
        "status": "completed",
        "call_id": "call_bc0a7fb7235840f69ecfe4",
        "name": "get_current_weather",
        "arguments": " {\"location\": \"Hangzhou\"}"
    }
}

response.content_part.added

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

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.content_part.added.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response. This value is always 0.

content_indexinteger

The index of the internal part within the output item. This value is always 0.

partobject

The output item information.

Properties

typestring

The type of the content part.

textstring

The text of the content part.

{
    "event_id": "event_AVBOmrgY3C8bjlRajfSUT",
    "type": "response.content_part.added",
    "response_id": "resp_HaVOPdbmX6vifiV5pAfJY",
    "item_id": "item_Ls6MtCUWO7LM4E59QziNv",
    "output_index": 0,
    "content_index": 0,
    "part": {
        "type": "audio",
        "text": ""
    }
}

response.content_part.done

Returned when streaming of a content part within an assistant message item finishes.

event_idstring

A unique identifier for this event.

typestring

The event type. This value is always response.content_part.done.

response_idstring

The response ID.

item_idstring

The message item ID.

output_indexinteger

The index of the output item in the response. This value is always 0.

content_indexinteger

The index of the content part in the content array. This value is always 0.

partobject

The output item information.

Properties

typestring

The type of the content part.

textstring

The text of the content part.

{
    "event_id": "event_Il8HD19v58Qr5IBkw7LtN",
    "type": "response.content_part.done",
    "response_id": "resp_HaVOPdbmX6vifiV5pAfJY",
    "item_id": "item_Ls6MtCUWO7LM4E59QziNv",
    "output_index": 0,
    "content_index": 0,
    "part": {
        "type": "audio",
        "text": "Hello! How can I help you?"
    }
}

MCP events

This section describes WebSocket events and fields for qwen3.8-omni-flash-realtime. Other base events and fields use the common protocol documented above. Required fields are required when their containing object is present. IDs are opaque strings; do not rely on their lengths, prefixes, or generation rules. arguments and output are strings whose contents require JSON parsing. MCP connections, discovery, and calls are subject to service quotas and timeouts.

mcp_list_tools.*

Event type	When emitted
`mcp_list_tools.in_progress`	Tool discovery starts for an MCP server.
`mcp_list_tools.completed`	Discovery succeeds and `allowed_tools` filtering completes.
`mcp_list_tools.failed`	Discovery fails, times out, or exceeds service limits.

event_idstring(Required)

Unique event ID.

typestring(Required)

Event type above.

item_idstring(Required)

Associated mcp_list_tools item.

in_progress can arrive before session.updated. For completed and failed, conversation.item.created containing the final tool list or error arrives first, followed by the status event with the same item_id.

{
  "event_id": "opaque_event_id",
  "type": "mcp_list_tools.completed",
  "item_id": "opaque_item_id"
}

response.mcp_call_arguments.delta

event_idstring(Required)

Unique event ID.

typestring(Required)

response.mcp_call_arguments.delta

response_idstring(Required)

Parent Response ID.

item_idstring(Required)

Current mcp_call item ID.

output_indexinteger(Required)

Zero-based index in the parent Response output array.

deltastring(Required)

Incremental JSON-string fragment; concatenate in event order.

obfuscationstring(Optional)

Optional obfuscation string; ignore when assembling and parsing arguments.

{
  "event_id": "opaque_event_id",
  "type": "response.mcp_call_arguments.delta",
  "response_id": "opaque_response_id",
  "item_id": "opaque_item_id",
  "output_index": 0,
  "delta": "{\"city\":\"杭",
  "obfuscation": "opaque-value"
}

response.mcp_call_arguments.done

event_idstring(Required)

typestring(Required)

response.mcp_call_arguments.done

response_idstring(Required)

item_idstring(Required)

output_indexinteger(Required)

Same meaning as above.

argumentsstring(Required)

Contains the complete JSON-encoded arguments and is authoritative.

{
  "event_id": "opaque_event_id",
  "type": "response.mcp_call_arguments.done",
  "response_id": "opaque_response_id",
  "item_id": "opaque_item_id",
  "output_index": 0,
  "arguments": "{\"city\":\"杭州\"}"
}

response.mcp_call.*

Event type	When emitted
`response.mcp_call.in_progress`	Arguments are complete and approval has been granted or is unnecessary; the MCP call starts.
`response.mcp_call.completed`	The MCP call succeeds.
`response.mcp_call.failed`	Connection, protocol, or tool business error; approval rejection or timeout; call timeout; or cancellation.

event_idstring(Required)

typestring(Required)

item_idstring(Required)

Identifies the current mcp_call.

output_indexinteger(Required)

Its index in the parent Response output array.

{
  "event_id": "opaque_event_id",
  "type": "response.mcp_call.in_progress",
  "item_id": "opaque_item_id",
  "output_index": 0
}

MCP conversation items

These objects are types of the item field in events, applicable to Qwen3.8-Omni-Flash-Realtime.

mcp_list_tools item

Returned as conversation.item.created.item; see the type=mcp_list_tools branch under conversation.item.created for its fields.

Example:

{
  "event_id": "opaque_event_id",
  "type": "conversation.item.created",
  "item": {
    "id": "opaque_item_id",
    "type": "mcp_list_tools",
    "server_label": "amap",
    "tools": [
      {
        "name": "maps_weather",
        "description": "查询天气",
        "input_schema": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "城市名"
            }
          },
          "required": ["city"]
        }
      }
    ]
  }
}

Initial mcp_call item

When the model selects an MCP tool, this item appears in response.output_item.added.item and may also appear in conversation.item.created.item; see the corresponding item branches under response.output_item.added and conversation.item.created.

response.output_item.added example:

{
  "event_id": "opaque_event_id",
  "type": "response.output_item.added",
  "response_id": "opaque_response_id",
  "output_index": 0,
  "item": {
    "id": "opaque_item_id",
    "object": "realtime.item",
    "type": "mcp_call",
    "status": "in_progress",
    "call_id": "opaque_call_id",
    "server_label": "amap",
    "name": "maps_weather",
    "arguments": ""
  }
}

mcp_approval_request item

Returned in conversation.item.created; see conversation.item.created for the event and approval item fields.

Example:

{
  "event_id": "opaque_event_id",
  "type": "conversation.item.created",
  "response_id": "opaque_response_id",
  "item_id": "opaque_approval_id",
  "previous_item_id": "opaque_item_id",
  "item": {
    "id": "opaque_approval_id",
    "type": "mcp_approval_request",
    "server_label": "amap",
    "name": "maps_weather",
    "arguments": "{\"city\":\"杭州\"}",
    "call_id": "opaque_call_id"
  }
}

Final mcp_call item

After a call reaches a terminal state, the item appears in response.output_item.done.item and in the final parent response.done.response.output snapshot; see the corresponding branches under response.output_item.done and response.done.

Success

Successful call:

{
  "event_id": "opaque_event_id",
  "type": "response.output_item.done",
  "response_id": "opaque_response_id",
  "output_index": 0,
  "item": {
    "id": "opaque_item_id",
    "type": "mcp_call",
    "status": "completed",
    "call_id": "opaque_call_id",
    "server_label": "amap",
    "name": "maps_weather",
    "arguments": "{\"city\":\"杭州\"}",
    "output": "{\"content\":[{\"type\":\"text\",\"text\":\"...\"}],\"isError\":false}"
  }
}

Failure

Failed call:

{
  "event_id": "opaque_event_id",
  "type": "response.output_item.done",
  "response_id": "opaque_response_id",
  "output_index": 0,
  "item": {
    "id": "opaque_item_id",
    "type": "mcp_call",
    "status": "failed",
    "call_id": "opaque_call_id",
    "server_label": "amap",
    "name": "maps_weather",
    "arguments": "{\"city\":\"杭州\"}",
    "error": {
      "type": "tool_execution_error",
      "message": "MCP tool call failed (call_timeout)."
    }
  }
}

MCP errors

MCP errors can occur during tool discovery or tool execution. For discovery errors, see error under the mcp_list_tools branch of conversation.item.created; for execution errors, see the mcp_call branch of response.output_item.done.

See Qwen-Omni-Realtime.