Fun-ASR client events

Client events are WebSocket commands that the client sends to the Fun-ASR real-time speech recognition service: run-task starts a recognition task, and finish-task ends it. User guide: For model details and selection guidance, see Speech-to-text models. Event sequence: For the event interaction diagram, see WebSocket API.

run-task

Description: Starts a speech recognition task. Sets the model, audio format, sample rate, and other parameters. When to send: Immediately after the WebSocket connection is established. Response: The client can send audio only after the service returns a task-started event.

Example

{
  "header": {
    "action": "run-task",
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "streaming": "duplex"
  },
  "payload": {
    "task_group": "audio",
    "task": "asr",
    "function": "recognition",
    "model": "fun-asr-realtime",
    "parameters": {
      "format": "pcm",
      "sample_rate": 16000
    },
    "input": {}
  }
}

object

body

required

Message header.

Show properties

string

body

required

The command type. Fixed at run-task.

string

body

required

A UUID-format task ID generated by the client. Subsequent events are correlated by this ID.

string

body

required

Fixed at duplex.

object

body

required

Message payload.

Show properties

string

body

required

The task group. Fixed at audio.

string

body

required

The task type. Fixed at asr.

string

body

required

The function type. Fixed at recognition.

string

body

required

The model name.

object

body

required

Fixed at {}.

object

body

required

Speech recognition parameters.

Show properties

string

body

required

The audio format. Valid values: pcm, wav, mp3, opus, speex, aac, amr.

integer

body

required

The sample rate, in Hz. 8 kHz models support only 8000 Hz; all other models support only 16000 Hz.

string

body

The custom vocabulary (hotword) list ID.

array[string]

body

The spoken language of the audio. No default; the model auto-detects the language when this parameter is omitted. Only the first value in the array is used; additional values are ignored. Valid values: zh (Chinese), en (English), ja (Japanese).

boolean

body

Whether to enable semantic punctuation. Default: false.

true: Enables semantic punctuation and disables VAD-based segmentation. Higher accuracy, suited for meeting transcription.
false (default): Enables VAD-based segmentation and disables semantic punctuation. Lower latency, suited for conversations.

integer

body

The VAD silence threshold, in milliseconds. When the silence after a speech segment exceeds this threshold, the system marks the sentence as ended. Default: 1300. Valid range: [200, 6000]. Effective only when semantic_punctuation_enabled is false.

boolean

body

Whether to enable multi-threshold mode. When enabled, prevents VAD from producing overly long segments. Default: false. Effective only when semantic_punctuation_enabled is false.

boolean

body

Whether to enable heartbeat packets. Default: false.

true: Keeps the connection alive even when the client continuously sends silent audio.
false (default): The connection times out and disconnects after 60 seconds, even when the client continuously sends silent audio.

float

body

The speech-noise discrimination threshold. Adjusts VAD sensitivity. Valid range: [-1.0, 1.0]. Only Fun-ASR supports this parameter.

Values closer to -1 lower the noise threshold. Noise is more likely to be classified as speech, which can cause additional noise to be transcribed.
Values closer to +1 raise the noise threshold. Speech is more likely to be classified as noise, which can cause some speech to be filtered out.

This is an advanced parameter. Small changes significantly affect recognition quality. Adjust in 0.1 steps and test thoroughly.

finish-task

Description: Notifies the service that all audio has been sent and requests that the service finish the task. When to send: After all audio data has been sent. Response: The service returns a task-finished event.

Example

{
  "header": {
    "action": "finish-task",
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "streaming": "duplex"
  },
  "payload": {
    "input": {}
  }
}

object

body

required

Message header.

Show properties

string

body

required

The command type. Fixed at finish-task.

string

body

required

A UUID-format task ID generated by the client. Must match the task_id used in the corresponding run-task event.

string

body

required

Fixed at duplex.

object

body

required

Message payload.

Show properties

object

body

required

Fixed at {}.

​run-task

​finish-task

run-task

finish-task