Qwen-Audio-ASR-Message real-time speech recognition server-side events

task-started

The task has started successfully. The client can begin sending audio data.

{
    "header": {
        "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
        "event": "task-started",
        "attributes": {}
    },
    "payload": {}
}

Parameter	Type	Description
header	object
header.task_id	string	The task ID generated by the client (in UUID format).
header.event	string	The event type. This value is always `task-started`.
header.attributes	object	Additional attributes. This value is usually empty.
payload	object	This value is always `{}`.

result-generated

Recognition results. By default, final sentence text is returned (sentence_end=true). Set intermediate_result_enabled=true to also receive intermediate text (sentence_end=false). Intermediate text may be revised: update the displayed text by sentence_id instead of concatenating it. A sentence-start event may contain sentence_begin=true and empty text. Sentence-start result:

{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "result-generated",
    "attributes": {}
  },
  "payload": {
    "output": {
      "sentence": {
        "sentence_id": 1,
        "begin_time": 0,
        "end_time": null,
        "text": "",
        "channel_id": 0,
        "speaker_id": null,
        "sentence_end": false,
        "sentence_begin": true,
        "words": []
      }
    }
  }
}

Final result:

{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "result-generated",
    "attributes": {}
  },
  "payload": {
    "output": {
      "sentence": {
        "sentence_id": 1,
        "begin_time": 120,
        "end_time": 1700,
        "text": "欢迎使用阿里云。",
        "channel_id": 0,
        "speaker_id": null,
        "sentence_end": true,
        "words": [
          {
            "begin_time": 120,
            "end_time": 520,
            "text": "欢迎",
            "punctuation": "",
            "fixed": false,
            "speaker_id": null
          },
          {
            "begin_time": 520,
            "end_time": 880,
            "text": "使用",
            "punctuation": "",
            "fixed": false,
            "speaker_id": null
          },
          {
            "begin_time": 880,
            "end_time": 1700,
            "text": "阿里云",
            "punctuation": "。",
            "fixed": false,
            "speaker_id": null
          }
        ],
        "stash": {
          "sentence_id": 2,
          "text": "",
          "begin_time": 1700,
          "current_time": 1700,
          "words": []
        }
      }
    },
    "usage": {
      "duration": 2,
      "input_tokens": 84,
      "output_tokens": 4,
      "total_tokens": 88
    }
  }
}

Parameter	Type	Description
header	object
header.task_id	string	The task ID generated by the client (in UUID format).
header.event	string	The event type. This value is always `result-generated`.
payload	object
payload.output	object
payload.output.sentence	object
payload.output.sentence.begin_time	integer	The start time of the sentence, in milliseconds.
payload.output.sentence.end_time	integer	The end time of the sentence, in milliseconds.
payload.output.sentence.text	string	The recognized text.
payload.output.sentence.heartbeat	boolean	If this value is true, the result is a heartbeat packet and can be ignored.
payload.output.sentence.sentence_begin	boolean	Indicates the start of a sentence.
payload.output.sentence.sentence_end	boolean	Whether the sentence has ended (true = final result, false = intermediate result).
payload.output.sentence.sentence_id	integer	The sequence identifier of the sentence. In normal recognition results, sentence_id increments from 1. When heartbeat is true (that is, a heartbeat packet), sentence_id is always 0.
payload.output.sentence.words	array[object]	Word-level timestamp information.
payload.output.sentence.words.begin_time	integer	The start time of the word, in milliseconds.
payload.output.sentence.words.end_time	integer	The end time of the word, in milliseconds.
payload.output.sentence.words.text	string	The recognized text.
payload.output.sentence.words.punctuation	string	The punctuation mark.
payload.usage	object	Cumulative usage for the current task as of this event.
payload.usage.duration	integer	Cumulative audio duration in seconds, retained for compatibility.
payload.usage.input_tokens	integer	Cumulative number of input tokens.
payload.usage.output_tokens	integer	Cumulative number of output tokens.
payload.usage.total_tokens	integer	Cumulative total number of tokens: the sum of `input_tokens` and `output_tokens`.

task-finished

The task has ended normally. You can close the connection or reuse it.

{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "task-finished",
    "attributes": {}
  },
  "payload": {
    "output": {},
    "usage": {
      "duration": 2,
      "input_tokens": 84,
      "output_tokens": 4,
      "total_tokens": 88
    }
  }
}

Parameter	Type	Description
header	object
header.task_id	string	The task ID generated by the client (in UUID format).
header.event	string	The event type. This value is always `task-finished`.
header.attributes	object	Additional attributes. This value is usually empty.
payload	object	Contains `output` (an empty object) and `usage` (the final cumulative usage for this task). The `usage` fields have the same definitions as in result-generated.

task-failed

The task has failed. The connection is closed and cannot be reused.

{
    "header": {
        "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
        "event": "task-failed",
        "error_code": "CLIENT_ERROR",
        "error_message": "request timeout after 23 seconds.",
        "attributes": {}
    },
    "payload": {}
}

Parameter	Type	Description
header	object
header.task_id	string	The task ID generated by the client (in UUID format).
header.event	string	The event type. This value is always `task-failed`.
header.error_code	string	A description of the error type.
header.error_message	string	The specific cause of the error.
header.attributes	object	Additional attributes. This value is usually empty.
payload	object	This value is always `{}`.

​task-started

​result-generated

​task-finished

​task-failed

task-started

result-generated

task-finished

task-failed