Qwen-Audio-TTS server events-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心

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_id string

The task ID generated by the client.

header.event string

Event type. Fixed value: task-started.

payload object

Empty 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_id string

The task ID generated by the client.

header.event string

Event type. Fixed value: result-generated.

payload.output object

Output information.

Properties

type string

Sub-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 usage information (usage).

sentence.index integer

Sentence index, starting from 0.

sentence.words array

Word-level timestamp array.

words element properties

text string

Text content of the word.

begin_index integer

Start character index of the word within the sentence. Starts at 0.

end_index integer

End character index of the word within the sentence. Starts at 1.

begin_time integer

Start time of the word's corresponding audio, in milliseconds.

end_time integer

End time of the word's corresponding audio, in milliseconds.

original_text string

Text of the sentence as segmented for synthesis.

payload.usage object

Billing usage, returned in the sentence-end event.

Noteqwen-audio-3.1-tts-flash is billed by input and output Tokens. qwen-audio-3.1-tts-plus, qwen-audio-3.0-tts-plus, and qwen-audio-3.0-tts-flash are billed by character.

Properties

input_tokens integer

Input token count for this request.

NoteApplies to qwen-audio-3.1-tts-plus, qwen-audio-3.1-tts-flash.

output_tokens integer

Output token count for this request.

NoteApplies to qwen-audio-3.1-tts-plus, qwen-audio-3.1-tts-flash.

total_tokens integer

Sum of input and output tokens.

NoteApplies to qwen-audio-3.1-tts-plus, qwen-audio-3.1-tts-flash.

characters integer

Cumulative number of billed characters.

sentence-begin

{
  "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,"
    }
  }
}

sentence-synthesis

{
    "header": {
        "task_id": "3f2d5c86-0550-45c0-801f-xxxxxxxxxx",
        "event": "result-generated",
        "attributes": {}
    },
    "payload": {
        "output": {
            "sentence": {
                "index": 0,
                "words": []
            },
            "type": "sentence-synthesis"
        }
    }
}

sentence-end

{
  "header": {
    "task_id": "3f2d5c86-0550-45c0-801f-xxxxxxxxxx",
    "event": "result-generated",
    "attributes": {}
  },
  "payload": {
    "output": {
      "sentence": {
        "index": 0,
        "words": [
          {
            "text": "Before",
            "begin_index": 0,
            "end_index": 1,
            "begin_time": 0,
            "end_time": 263
          }
        ]
      },
      "type": "sentence-end",
      "original_text": "Before my bed, moonlight shines bright,"
    },
    "usage": {
      "characters": 6
    }
  }
}

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_id string

The task ID generated by the client.

header.event string

Event type. Fixed value: task-finished.

payload.usage object

The fields are the same as usage in result-generated.

{
  "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_id string

The task ID generated by the client.

header.event string

Event type. Fixed value: task-failed.

header.error_code string

Error code.

header.error_message string

Detailed 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": {}
}