time audio and video translation - Qwen-Livetranslate-Realtime-Server events

Server-side events for the qwen3-livetranslate-flash-realtime API.

Reference: Real-time audio and video translation - Qwen

error

Error message returned by the server. **event_id **string* *The unique identifier for this event.

{
 "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"
 }
}

   **type **`*string*`* *The event type. The value is always `error`.   **error **`*object*`* *Detailed information about the error.

Properties

**type **string* * The error type.

**code **string* * The error code.

**message ***string* The error message.

**param ***string* The parameter that is related to the error, such as session.modalities.

session.created

When a client connects, the server returns this event first with the default session configurations. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_QxBGpjBDmDDQQWDtrqBKB",
 "type": "session.created",
 "session": {
 "id": "sess_OozZ1vtbPt2muDflHODIH",
 "object": "realtime.session",
 "model": "qwen3-livetranslate-flash-realtime",
 "modalities": \[
 "text",
 "audio"
 \],
 "voice": "Cherry",
 "input_audio_format": "pcm16",
 "output_audio_format": "pcm24",
 "translation": {
 "language": "en"
 }
 }
}

   **type **`*string*`* *The event type. The value is always `session.created`.   **session **`*object*`* *The session configuration.

Properties

**id **string* * The unique identifier for the session.

**object **string* * The value is always realtime.session.

**model **string* * The model in use.

**modalities **array* * The output modality settings for the model.

**voice **string* * The voice for the audio generated by the model.

**input_audio_format ***string* The format of the input audio. The value is always pcm16.

**output_audio_format ***string* The format of the output audio. The value is always pcm24.

**translation **object* *(Optional) The translation configuration. Properties

translation *string* (Optional) The target language for translation.

session.updated

Returned after a successful session.update request. If the request fails, an error event is returned instead. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_QxBGpjBDmDDQQWDtrqBKB",
 "type": "session.updated",
 "session": {
 "id": "sess_OozZ1vtbPt2muDflHODIH",
 "object": "realtime.session",
 "model": "qwen3-livetranslate-flash-realtime",
 "modalities": \[
 "text",
 "audio"
 \],
 "voice": "Ethan",
 "input_audio_format": "pcm16",
 "output_audio_format": "pcm24",
 "translation": {
 "language": "en"
 }
 }
}

   **type **`*string*`* *The event type. The value is always `session.updated`.   **session **`*object*`* *The session configuration.

Properties

**id **string* * The unique identifier for the session.

**object **string* * The value is always realtime.session.

**model **string* * The model in use.

**modalities **array* * The output modality settings for the model.

**voice **string* * The voice for the audio generated by the model.

**input_audio_format ***string* The format of the input audio. The value is always pcm16.

**output_audio_format ***string* The format of the output audio. The value is always pcm24.

**translation **object* *(Optional) The translation configuration. Properties

translation *string* (Optional) The target language for translation.

session.finished

Session is finished and all audio translations are complete.

Sent only after the client sends a session.finish request. The client can then disconnect. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_xxx",
 "type": "session.finished"
}

   **type **`*string*`* *The event type. The value is always `session.finished`.

response.created

Returned when the server generates a new model response. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_L8hHVI5jYis6BzAjnPWJh",
 "type": "response.created",
 "response": {
 "id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "object": "realtime.response",
 "conversation_id": "conv_UFClXtYkRkFXrs48y8pmK",
 "status": "in_progress",
 "modalities": \[
 "text",
 "audio"
 \],
 "voice": "Cherry",
 "output_audio_format": "pcm24",
 "output": \[\]
 }
}

   **type **`*string*`* *The event type. The value is always `response.created`.   **response **`*object*`* *The response object.

Properties

id *string** * The unique identifier for the response.

conversation_id *string** * The unique identifier for the current session.

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

status *string** * The response status. Valid values:

• completed
• failed
• in_progress
• incomplete

modalities *array** * Response modality.

voice *string** * The voice of the generated audio.

output_audio_format *string* The format of the output audio. The value is fixed to pcm24.

output *string* This event is currently empty.

response.done

Returned after response generation is complete. Contains all output items except raw audio data. event_id *string** *The unique identifier for this event.

{
 "event_id": "event_CNea8oXNipVanSg2VIzkO",
 "type": "response.done",
 "response": {
 "id": "resp_TfhYTqej692vsGA2jNEtH",
 "object": "realtime.response",
 "conversation_id": "conv_ZtyLfKVm8XqLwYRlsuDih",
 "status": "completed",
 "modalities": \[
 "text",
 "audio"
 \],
 "voice": "Cherry",
 "output_audio_format": "pcm24",
 "output": \[
 {
 "id": "item_MKtkMwN9RtcyE9eJShyWy",
 "object": "realtime.item",
 "type": "message",
 "status": "completed",
 "role": "assistant",
 "content": \[
 {
 "type": "audio",
 "transcript": "Hello? "
 }
 \]
 }
 \],
 "usage": {
 "total_tokens": 56,
 "input_tokens": 47,
 "output_tokens": 9,
 "input_tokens_details": {
 "text_tokens": 20,
 "audio_tokens": 27
 },
 "output_tokens_details": {
 "text_tokens": 2,
 "audio_tokens": 7
 }
 }
 }
}

   **type** `*string*`* *The event type. The value is always `response.done`.   **response** `*object*`* *The response object.

Properties

id *string** * The unique identifier for the response.

conversation_id *string** * The unique identifier for the current session.

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

status *string** * The status of the response.

modalities *array** * The modality of the response.

voice *string** * The voice used for the audio generated by the model.

output_audio_format *string* The format of the output audio. The value is always pcm24.

output *object** * The output of the response. Properties

id *string** * The unique identifier for the response output.

type *string** * The type of the output item. The value is currently always message.

object *string** * The object type of the output item. The value is currently always realtime.item.

status *string** * The status of the output item.

role *string** * The role of the output item.

content *array** * The content of the output item. Properties

type *string** * The type of the output content. The value is text for plain text output and audio when the output includes audio.

text *string** * The text content of the output.

transcript *string** * The text transcription of the audio content.

usage *object** * The token consumption information for this response.

response.text.text

Returned for text-only output when the model generates text incrementally. **event_id **string* *A unique identifier for the event.

{
 "event_id": "event_B1lIeyOXR7qJMEExbqtTG",
 "type": "response.text.text",
 "response_id": "resp_B1lIdtjF4Noqpn5NOjznj",
 "item_id": "item_B1lIdJsAJlJiFs8ztWpJt",
 "output_index": 0,
 "content_index": 0,
 "text": "How are",
 "stash": " you today?"
}

   **type **`*string*`* *The type of the event. The value is always `response.text.text`.   **text **`*string*`* *The incremental text that is returned.   **response_id **`*string*`* *The response ID.   **item_id **`*string*`* *A unique identifier for the message item.   **output_index **`*integer*`* *Currently, the value is always 0.   **content_index **`*integer*`* *Currently, the value is always 0.   **stash **`*string*`A temporary text generated by the model. Concatenate this with the current `text` to form a temporary result. The system updates `text` and `stash` continuously using `response.text.text` events until it receives a response.text.done event. At that point, get the final full text from the `text` field.

response.text.done

Returned when text generation finishes for text-only output, or if the response is interrupted, incomplete, or canceled. **event_id **string* *The unique identifier for this event.

{
 "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?"
}

   **type **`*string*`* *The event type. The value is always `response.text.done`.   **response_id **`*string*`* *The unique identifier for the response.   **item_id **`*string*`* *The unique identifier for the message item.   **output_index **`*integer*`* *The value is currently always 0.   **content_index **`*integer*`* *The value is currently always 0.   **text** `*string*`* *The complete text output from the model.

response.audio.delta

Returned when audio output is enabled and the model generates audio incrementally. **event_id **string* *A unique identifier for the event.

{
 "event_id": "event_B1osWMZBtrEQbiIwW0qHQ",
 "type": "response.audio.delta",
 "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "item_id": "item_OFaPGtzfWCPyGzxnuEX9i",
 "output_index": 0,
 "content_index": 0,
 "delta": "UklGRnoGAABXQVZFZm10IBAAAAAB..."
}

   **type **`*string*`* *The event type. The value is always `response.audio.delta`.   **response_id **`*string*`* *A unique identifier for the response.   **item_id **`*string*`* *A unique identifier for the message item.   **output_index** *integer*The value is always 0.   **content_index** `*integer*`* *The value is always 0.   **delta** `*string*`The incremental audio data that is output by the model. The data is Base64-encoded.

response.audio.done

Returned when audio generation is complete. Also returned if the response is interrupted, incomplete, or canceled. Does not contain complete audio data. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_B1osWMWoDRYyITDyNYcBu",
 "type": "response.audio.done",
 "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "item_id": "item_OFaPGtzfWCPyGzxnuEX9i",
 "output_index": 0,
 "content_index": 0
}

   **type **`*string*`* *The event type. This is always `response.audio.done`.   **response_id **`*string*`* *The unique identifier for the response.   **item_id **`*string*`* *The unique identifier for the message item.   **output_index **`*integer*`* *The value is always 0.   **content_index **`*integer*`* *The value is always 0.

conversation.item.input_audio_transcription.text

When input_audio_transcription.model is configured, the server streams speech recognition results in the original source language. **event_id ***string*The unique identifier for this event.

{
 "event_id": "event_xxx",
 "type": "conversation.item.input_audio_transcription.text",
 "item_id": "item_xxx",
 "content_index": 0,
 "text": "",
 "stash": "The weather is really nice today",
 "language": "zh"
}

   **type **`*string*`The event type. The value is always `conversation.item.input_audio_transcription.text`.   **item_id **`*string*`The unique identifier for the message item.   **content_index **`*integer*`The value is currently always 0.   **text **`*string*`The confirmed recognition text.   **stash **`*string*`The recognition text that is pending confirmation. This text may be corrected by subsequent events.   **language **`*string*`The detected source language.

conversation.item.input_audio_transcription.completed

When input_audio_transcription.model is configured, returns the final recognition result after speech recognition completes. **event_id ***string*The unique identifier for this event.

{
 "event_id": "event_xxx",
 "type": "conversation.item.input_audio_transcription.completed",
 "item_id": "item_xxx",
 "content_index": 0,
 "transcript": "The weather is really nice today, let's go for a walk in the park.",
 "language": "zh"
}

   **type **`*string*`The event type. This is always `conversation.item.input_audio_transcription.completed`.   **item_id **`*string*`The unique identifier for the message item.   **content_index **`*integer*`This is currently always 0.   **transcript **`*string*`The complete speech recognition result in the original source language.   **language **`*string*`The detected source language.

response.audio_transcript.text

Returned for audio output to display real-time translation. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_xxx",
 "type": "response.audio_transcript.text",
 "response_id": "resp_xxx",
 "item_id": "item_xxx",
 "output_index": 0,
 "content_index": 0,
 "text": "Hello,",
 "stash": " who are you?"
}

   **type **`*string*`* *The type of the event. The value is always `response.audio_transcript.text`.   **response_id **`*string*`* *The unique identifier for the response.   **item_id **`*string*`* *The unique identifier for the message item.   **output_index** `*integer*`* *Currently, the value is always 0.   **content_index** `*integer*`* *Currently, the value is always 0.   **text **`*string*`* *The confirmed translation text segment.   **stash **`*string*`* *Temporary translation text, concatenated with `text` to form interim results. The system updates `text` and `stash` continuously via `response.audio_transcript.text` events until a response.audio_transcript.done event is received. Then retrieve the final translation from `transcript`.

response.audio_transcript.done

Returned when audio output is enabled and text generation finishes. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_VN4Q4GJugLcc1S23viW8E",
 "type": "response.audio_transcript.done",
 "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "item_id": "item_JvJauNH2CTXb1D9WV6pD4",
 "output_index": 0,
 "content_index": 0,
 "transcript": "How can I assist you today?"
}

   **type **`*string*`* *The event type. This is always `response.audio_transcript.done`.   **response_id **`*string*`* *The unique identifier for the response.   **item_id **`*string*`* *The unique identifier for the message item.   **output_index** `*integer*`* *This is currently always 0.   **content_index** `*integer*`* *This is currently always 0.   **transcript **`*string*`* *The complete text.

response.output_item.added

Returned when a new output item is added during response generation. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_B4O5yPt3Gjnjy5eYH3plG",
 "type": "response.output_item.added",
 "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "output_index": 0,
 "item": {
 "id": "item_OFaPGtzfWCPyGzxnuEX9i",
 "object": "realtime.item",
 "type": "message",
 "status": "in_progress",
 "role": "assistant",
 "content": \[\]
 }
}

   **type **`*string*`* *The event type. The value is always `response.output_item.added`.   **response_id **`*string*`* *The unique identifier for the response.   **output_index** `*integer*`* *The value is currently always 0.   **item** `*object*`* *Information about the output item.

Properties

**id **string* * The unique identifier for the output item.

**type **string* * The value is always message.

**object **string* * The value is always realtime.item.

**status **string* * The status of the output item.

**role **string* * The role of the message.

**content **string* * The content of the message.

response.output_item.done

Returned when an output item is completed. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_XkiwbYTBC9Wcdwy6uYJ2G",
 "type": "response.output_item.done",
 "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "output_index": 0,
 "item": {
 "id": "item_JvJauNH2CTXb1D9WV6pD4",
 "object": "realtime.item",
 "type": "message",
 "status": "completed",
 "role": "assistant",
 "content": \[
 {
 "type": "audio",
 "text": "Hello, I am a large language model developed by Alibaba Cloud. My name is Qwen. How can I help you?"
 }
 \]
 }
}

   **type **`*string*`* *The event type. The value is always `response.output_item.done`.   **response_id **`*string*`* *The unique identifier for the response.   **output_index **`*integer*`* *The value is currently always 0.   **item **`*object*`* *Information about the output item.

Properties

**id **string* * The unique identifier for the output item.

**object **string* * The value is always realtime.item.

**type **string* * The value is always message.

**status **string* * The status of the output item.

**role **string* * The role of the message sender.

**content **string* * The content of the message.

response.content_part.added

Returned when a new content part is added. event_id *string*The unique ID of the event.

{
 "event_id": "event_J2UixwYKZsXg7c9YXZetL",
 "type": "response.content_part.added",
 "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "item_id": "item_OFaPGtzfWCPyGzxnuEX9i",
 "output_index": 0,
 "content_index": 0,
 "part": {
 "type": "audio",
 "text": ""
 }
}

   **type** `*string*`The type of the event. The value is always `response.content_part.added`.   **response_id** `*string*`The unique ID of the response.   **item_id** `*string*`The unique ID of the message item.   **output_index** `*integer*`The value is always 0.   **content_index** `*integer*`The value is always 0.   **part** `*object*`Outputs item information.

Properties

type *string* The type of the content part.

text *string* The text of the content part.

response.content_part.done

Returned when a content part is completed. **event_id **string* *The unique identifier for this event.

{
 "event_id": "event_VN4Q4GJugLcc1S23viW8E",
 "type": "response.content_part.done",
 "response_id": "resp_P79OOMs8LnrXVpiIHUCKR",
 "item_id": "item_JvJauNH2CTXb1D9WV6pD4",
 "output_index": 0,
 "content_index": 0,
 "part": {
 "type": "audio",
 "text": "Hello, I am a large language model developed by Alibaba Cloud. My name is Qwen. How can I help you?"
 }
}

   **type **`*string*`* *The event type. This is always `response.content_part.done`.   **response_id **`*string*`* *The unique identifier for the response.   **item_id **`*string*`* *The unique identifier for the message item.   **output_index** `*integer*`* *The value is always 0.   **content_index** `*integer*`* *The value is always 0.   **part** `*object*`* *Information about the content part.

Properties

**type **string* * The type of the content part.

**text **string* * The text of the content part.