Skip to main content
Real-time speech synthesis (Qwen-Audio-TTS/CosyVoice)

Qwen-Audio-TTS/CosyVoice server-side events

User guide: For model introduction and selection recommendations, see Speech synthesis.

task-started

After the client sends the run-task command, the server returns a task-started event to signal that the task has started. The client can send subsequent commands only after receiving this event.
header.task_idstringThe task ID generated by the client.header.eventstringEvent type. Fixed value: task-started.payloadobjectEmpty object.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "task-started",
    "attributes": {}
  },
  "payload": {}
}

result-generated

After the client sends text, the server continuously returns result-generated events. Each event carries sentence-level metadata.
header.task_idstringThe task ID generated by the client.header.eventstringEvent type. Fixed value: result-generated.payload.outputobjectOutput information.

Properties

typestringSub-event type. Valid values:
  • sentence-begin: Sentence start. Returns the text to be synthesized.
  • sentence-synthesis: Marks an audio frame. One audio frame is transmitted over the WebSocket binary channel immediately after each event.
  • sentence-end: Sentence end. Returns the text content and cumulative character count.
sentence.indexintegerSentence index, starting from 0.sentence.wordsarrayWord-level timestamp array.

words element properties

textstringText content of the word.begin_indexintegerStart character index of the word within the sentence. Starts at 0.end_indexintegerEnd character index of the word within the sentence. Starts at 1.begin_timeintegerStart time of the word's corresponding audio, in milliseconds.end_timeintegerEnd time of the word's corresponding audio, in milliseconds.
original_textstringText of the sentence as segmented for synthesis.
payload.usageobjectBilling information, returned in the sentence-end event.

Properties

charactersintegerCumulative number of billed characters.
{
  "header": {
    "task_id": "3f2d5c86-0550-45c0-801f-xxxxxxxxxx",
    "event": "result-generated",
    "attributes": {}
  },
  "payload": {
    "output": {
      "sentence": {
        "index": 0,
        "words": []
      },
      "type": "sentence-begin",
      "original_text": "Before my bed, moonlight shines bright,"
    }
  }
}

task-finished

The server returns a task-finished event when the task completes. The client can then close the WebSocket connection or reuse it to start a new task.
header.task_idstringThe task ID generated by the client.header.eventstringEvent type. Fixed value: task-finished.payload.usage.charactersintegerCumulative number of billed characters.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "task-finished",
    "attributes": {
      "request_uuid": "0a9dba9e-d3a6-45a4-be6d-xxxxxxxxxxxx"
    }
  },
  "payload": {
    "usage": {
      "characters": 13
    }
  }
}

task-failed

The server returns a task-failed event when the task fails. On receiving this event, the client must close the WebSocket connection and handle the error.
header.task_idstringThe task ID generated by the client.header.eventstringEvent type. Fixed value: task-failed.header.error_codestringError code.header.error_messagestringDetailed error message.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "task-failed",
    "error_code": "InvalidParameter",
    "error_message": "[tts:]Engine return error code: 418",
    "attributes": {}
  },
  "payload": {}
}
Text Generation
Image Generation
  • FAQ
Video Generation
Audio
Realtime API
Text Embedding
Model Production
Qwen-Audio-TTS/CosyVoice server-side events - Alibaba Cloud Model Studio