Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR非实时语音识别Python SDK

from http import HTTPStatus
from dashscope.audio.asr import Transcription
import dashscope
import os
import json

# 以下为新加坡地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# 新加坡地域和北京地域的API Key不同。获取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# 若没有配置环境变量，请用百炼API Key将下行替换为：dashscope.api_key = "sk-xxx"
dashscope.api_key = os.getenv("DASHSCOPE_API_KEY")

transcribe_response = Transcription.async_call(
    model='qwen-audio-3.0-asr-flash-filetrans',
    file_urls=['{YOUR_AUDIO_URL}']
)

while True:
    if transcribe_response.output.task_status == 'SUCCEEDED' or transcribe_response.output.task_status == 'FAILED':
        break
    transcribe_response = Transcription.fetch(task=transcribe_response.output.task_id)

if transcribe_response.status_code == HTTPStatus.OK:
    print(json.dumps(transcribe_response.output, indent=4, ensure_ascii=False))
    print('transcription done!')

{
    "file_url":"{YOUR_AUDIO_URL}",
    "properties":{
        "audio_format":"pcm_s16le",
        "channels":[
            0
        ],
        "original_sampling_rate":16000,
        "original_duration_in_milliseconds":3834
    },
    "transcripts":[
        {
            "channel_id":0,
            "content_duration_in_milliseconds":3720,
            "text":"Hello world, 这里是阿里巴巴语音实验室。",
            "sentences":[
                {
                    "begin_time":100,
                    "end_time":3820,
                    "text":"Hello world, 这里是阿里巴巴语音实验室。",
                    "sentence_id":1,
                    "speaker_id":0, //当开启自动说话人分离功能时才会显示该字段
                    "words":[
                        {
                            "begin_time":100,
                            "end_time":596,
                            "text":"Hello ",
                            "punctuation":""
                        },
                        {
                            "begin_time":596,
                            "end_time":844,
                            "text":"world",
                            "punctuation":", "
                        }
                        // 这里省略其它内容
                    ]
                }
            ]
        }
    ]
}