headerobject Properties task_idstring The task ID generated by the client (in UUID format). eventstring The event type. This value is always result-generated. payloadobject Properties outputobject Properties sentenceobject Properties begin_timeinteger The start time of the sentence, in milliseconds. end_timeinteger The end time of the sentence, in milliseconds. textstring The recognized text. heartbeatboolean If this value is true, the result is a heartbeat packet and can be ignored. sentence_beginboolean Indicates the start of a sentence. sentence_endboolean Whether the sentence has ended (true = final result, false = intermediate result). sentence_idinteger 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. wordsarray[object] Word-level timestamp information. Properties begin_timeinteger The start time of the word, in milliseconds. end_timeinteger The end time of the word, in milliseconds. textstring The recognized text. punctuationstring The punctuation mark. usageobject Cumulative usage for the current task. Properties input_tokensinteger Cumulative input tokens. NoteApplies to qwen-audio-3.1-asr-flash-streaming. output_tokensinteger Cumulative output tokens. NoteApplies to qwen-audio-3.1-asr-flash-streaming. total_tokensinteger Total cumulative tokens, equal to the sum of input and output tokens. NoteApplies to qwen-audio-3.1-asr-flash-streaming. durationinteger Cumulative audio duration, in seconds. NoteUsed for billing for qwen-audio-3.0-asr-flash-streaming. | Sentence-start result:{
"header": {
"task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
"event": "result-generated",
"attributes": {}
},
"payload": {
"output": {
"sentence": {
"begin_time": 0,
"end_time": null,
"text": "",
"sentence_begin": true,
"sentence_end": false,
"sentence_id": 1,
"words": []
}
}
}
}
Final result:{
"header": {
"task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
"event": "result-generated",
"attributes": {}
},
"payload": {
"output": {
"sentence": {
"sentence_id": 1,
"begin_time": 160,
"end_time": 1640,
"text": "欢迎使用阿里云。",
"channel_id": 0,
"speaker_id": null,
"sentence_end": true,
"words": [
{
"begin_time": 160,
"end_time": 520,
"text": "欢迎",
"punctuation": "",
"fixed": true,
"speaker_id": null
},
{
"begin_time": 520,
"end_time": 880,
"text": "使用",
"punctuation": "",
"fixed": true,
"speaker_id": null
},
{
"begin_time": 880,
"end_time": 1640,
"text": "阿里云",
"punctuation": "。",
"fixed": true,
"speaker_id": null
}
],
"stash": {
"sentence_id": 2,
"text": "",
"begin_time": 1640,
"current_time": 1640,
"words": []
}
},
"text": "欢迎使用阿里云。",
"request_id": "95372ce8e6704bcc8747da94789c15ca",
"output": {
"sentence": {
"sentence_id": 1,
"begin_time": 160,
"end_time": 1640,
"text": "欢迎使用阿里云。",
"channel_id": 0,
"speaker_id": null,
"sentence_end": true,
"words": [
{
"begin_time": 160,
"end_time": 520,
"text": "欢迎",
"punctuation": "",
"fixed": true,
"speaker_id": null
},
{
"begin_time": 520,
"end_time": 880,
"text": "使用",
"punctuation": "",
"fixed": true,
"speaker_id": null
},
{
"begin_time": 880,
"end_time": 1640,
"text": "阿里云",
"punctuation": "。",
"fixed": true,
"speaker_id": null
}
],
"stash": {
"sentence_id": 2,
"text": "",
"begin_time": 1640,
"current_time": 1640,
"words": []
}
},
"text": "欢迎使用阿里云。",
"request_id": "95372ce8e6704bcc8747da94789c15ca"
},
"usage": {
"duration": 2,
"input_tokens": 85,
"output_tokens": 4,
"total_tokens": 89
}
},
"usage": {
"duration": 2,
"input_tokens": 85,
"output_tokens": 4,
"total_tokens": 89
}
}
}
|