Client events - Alibaba Cloud Model Studio

Reference: Real-time audio and video translation - Qwen .

session.update

Send this event after establishing a WebSocket connection to update the default session configuration. The server validates parameters and returns either an error (if invalid) or the updated configuration (if valid).

typestring(Required)Event type. Must be set to session.update.sessionobject(Optional)The session configuration.

Properties

modalitiesarray(Optional)Output modalities. Valid values:

["text"] Outputs text only.
["text","audio"] (Default) Outputs text and audio.

voicestring(Optional)Voice for generated audio. When voice cloning is disabled, set this to a system preset voice. Valid values: Supported voices. Default value: Tina for Qwen3.5-LiveTranslate-Flash-Realtime, or Cherry for Qwen3-LiveTranslate-Flash-Realtime.

When enable_voice_clone is true, the value of voice depends on the frequency setting. When frequency is once or always, set it to default. When frequency is never, set it to the voice ID you previously cloned. Using a system preset voice in this case causes a server error.

enable_voice_cloneboolean(Optional)Whether to enable voice cloning. Default value: false. When enabled, the model clones the speaker's voice from the input audio for translated output. In this case, voice no longer accepts system preset voices and must be set to default or a voice ID previously created through the Voice Clone API.voice_clone_optionsobject(Optional)Voice clone control options. Takes effect only when enable_voice_clone is true.

Properties

voice_clone_options.frequencystring(Optional)Voice cloning frequency. Valid values:

never Disables server-side voice cloning and uses a voice you previously cloned. Set voice to your cloned voice ID.
once Clones the voice once at the start of the session and reuses it for all subsequent output. Suitable for single-speaker scenarios. Set voice to default.
always Re-clones the voice in real time before each output, dynamically adapting to the input audio. Suitable for multi-speaker scenarios. Set voice to default.

sample_rateinteger(Optional)Input audio sample rate, in Hz. Valid values:

8000
16000 (Default)

input_audio_transcriptionobject(Optional)Configuration for input audio.

Properties

modelstring(Optional)Speech recognition model. If configured, the server returns both the recognition result (original source language text) and translation via the conversation.item.input_audio_transcription.text and conversation.item.input_audio_transcription.completed events.Valid value: qwen3-asr-flash-realtime.languagestring(Optional)Source language for translation. Valid values: Supported languages. If not specified, the model automatically detects the source language.

input_audio_formatstring(Optional)Input audio format. Valid values:

pcm (Default) Uncompressed raw audio data.
opus Lossy audio codec with low-latency support, suitable for VoIP scenarios.

output_audio_formatstring(Optional)Output audio format. Currently, this parameter can only be set to pcm.turn_detectionobject(Optional)Voice Activity Detection (VAD) configuration, used to control how speech start and end are detected:

Set to a configuration object (default): Enables VAD mode. The server automatically detects speech start and end, commits the audio buffer, and triggers translation responses. The client does not need to send input_audio_buffer.commit events.
Set to null: Enables Manual mode. The client manually commits the audio buffer by sending input_audio_buffer.commit events. The server automatically starts generating translation responses upon receiving the commit.

Properties

typestring(Optional)VAD type. Must be set to server_vad.thresholdfloat(Optional)VAD detection sensitivity. A lower value makes it easier to recognize faint sounds (including background noise) as speech; a higher value requires clearer, louder speech to trigger detection.Value range: [-1.0, 1.0]. Default value: 0.2.silence_duration_msinteger(Optional)Minimum duration of silence (in milliseconds) required after speech ends. Once this duration is exceeded, the server determines that speech has ended, automatically commits the audio buffer, and triggers a translation response.Value range: [200, 6000]. Default value: 1000.

translationobject(Optional)Translation configuration.

Properties

languagestring(Optional)Target language for translation. Valid values: Supported languages. Default value: en.same_language_skip_optionsobject(Optional)Same-language output configuration. When the source and target languages are the same, the service can skip text output, audio output, or both. This parameter takes effect only when translation.language is set to zh or en.

Properties

skip_textboolean(Optional)Specifies whether to skip text output when the source and target languages are the same.skip_audioboolean(Optional)Specifies whether to skip audio output when the source and target languages are the same.

corpusobject(Optional)Hot-word configuration to improve translation accuracy for specific terms.

Properties

phrasesobject(Optional)Hot-word mapping. The key is the term in the source language, and the value is its target-language translation.Example: {"AI": "Artificial Intelligence"}

{
  "event_id": "event_ToPZqeobitzUJnt3QqtWg",
  "type": "session.update",
  "session": {
    "modalities": [
      "text",
      "audio"
    ],
    "voice": "Cherry",
    "sample_rate": 16000,
    "input_audio_format": "pcm",
    "output_audio_format": "pcm",
    "input_audio_transcription": {
      "model": "qwen3-asr-flash-realtime",
      "language": "zh"
    },
    "translation": {
      "language": "en",
      "corpus": {
        "phrases": {
          "人工智能": "Artificial Intelligence",
          "机器学习": "Machine Learning"
        }
      }
    }
  }
}

Example with voice clone enabled (frequency=once):

{
  "event_id": "event_ToPZqeobitzUJnt3QqtWg",
  "type": "session.update",
  "session": {
    "modalities": [
      "text",
      "audio"
    ],
    "voice": "default",
    "enable_voice_clone": true,
    "voice_clone_options": {
      "frequency": "once"
    },
    "sample_rate": 16000,
    "input_audio_format": "pcm",
    "output_audio_format": "pcm",
    "translation": {
      "language": "en"
    }
  }
}

Example with both the source and target languages set to English and text and audio output skipped:

{
  "event_id": "event_xxx",
  "type": "session.update",
  "session": {
    "input_audio_transcription": {
      "language": "en"
    },
    "translation": {
      "language": "en",
      "same_language_skip_options": {
        "skip_text": true,
        "skip_audio": true
      }
    }
  }
}

input_audio_buffer.append

Appends audio bytes to the input audio buffer. The service uses this buffer to detect speech and determine when to submit it.

typestring(Required)Event type. Must be set to input_audio_buffer.append.audiostring(Required)Base64-encoded audio data.

{
    "event_id": "event_xxx",
    "type": "input_audio_buffer.append",
    "audio": "xxx"
}

input_audio_buffer.commit

Commits the input audio buffer. This event only needs to be sent in Manual mode (turn_detection set to null). In VAD mode, the server commits automatically and the client does not need to send this event. Upon receiving this event, the server returns an input_audio_buffer.committed event as confirmation and automatically starts generating a translation response (no additional event is needed to trigger the response). If the audio buffer is empty, the server returns an error event.

typestring(Required)Event type. Must be set to input_audio_buffer.commit.

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

input_audio_buffer.clear

Clears uncommitted audio data from the input audio buffer.

typestring(Required)Event type. Must be set to input_audio_buffer.clear.

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

input_image_buffer.append

Adds image data to the image buffer from a local file or real-time video stream. Image input limits:

Image format: JPG or JPEG. Recommended resolution for optimal performance: 480p or 720p (maximum: 1080p).
Maximum image size: 500 KB (before Base64 encoding).
Image data must be Base64-encoded.
Maximum frequency: 2 images per second.
Send at least one input_audio_buffer.append event before sending input_image_buffer.append.

typestring(Required)Event type. Must be set to input_image_buffer.append.imagestring(Required)Base64-encoded image data.

{
    "event_id": "event_xxx",
    "type": "input_image_buffer.append",
    "image": "xxx"
}

session.finish

Send this event to end the current session. Server responses:

If speech is detected: Server completes speech recognition, sends conversation.item.input_audio_transcription.completed with the recognition result, then sends session.finished to indicate session end.
If no speech is detected: Server sends session.finished directly.

The client must disconnect after receiving session.finished.

typestring(Required)Event type. Must be set to session.finish.

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

​session.update

​input_audio_buffer.append

​input_audio_buffer.commit

​input_audio_buffer.clear

​input_image_buffer.append

​session.finish

session.update

input_audio_buffer.append

input_audio_buffer.commit

input_audio_buffer.clear

input_image_buffer.append

session.finish