Category: provider
Model Studio Qwen ASR Realtime
Validation
CODEBLOCK0
Pass criteria: command exits 0 and output/aliyun-qwen-asr-realtime/validate.txt is generated.
Output And Evidence
- - Save session payloads and response samples under
output/aliyun-qwen-asr-realtime/.
Critical model names
Use one of these exact model strings:
Use cases
- - Realtime subtitles and captions
- Voice-agent duplex input
- Streaming speech-to-text in browser or terminal clients
Prerequisites
- - Set
DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials. - Realtime sessions generally require WebSocket or streaming session handling in the client.
Normalized interface (asr.realtime)
Request
- -
model (string, optional): default INLINECODE8 - INLINECODE9 (array, optional)
- INLINECODE10 (string, optional): e.g.
pcm, INLINECODE12 - INLINECODE13 (int, optional): e.g. INLINECODE14
- INLINECODE15 (int, optional): frame size in milliseconds
Response
- -
text (string): recognized transcript fragment - INLINECODE17 (bool): finalization marker
- INLINECODE18 (object, optional)
Quick start
Generate a request template:
CODEBLOCK1
Operational guidance
- - Prefer 16kHz mono PCM unless your client stack requires another format.
- Keep chunks small enough for responsive partial results.
- If you only have recorded files, use
skills/ai/audio/aliyun-qwen-asr/ instead.
References
技能名称: aliyun-qwen-asr-realtime
详细描述:
类别: provider
Model Studio Qwen ASR 实时
验证
bash
mkdir -p output/aliyun-qwen-asr-realtime
python -m pycompile skills/ai/audio/aliyun-qwen-asr-realtime/scripts/preparerealtimeasrrequest.py && echo pycompileok > output/aliyun-qwen-asr-realtime/validate.txt
通过标准:命令退出码为 0,且生成了 output/aliyun-qwen-asr-realtime/validate.txt 文件。
输出与证据
- - 将会话负载和响应样本保存到 output/aliyun-qwen-asr-realtime/ 目录下。
关键模型名称
使用以下精确的模型字符串之一:
- - qwen3-asr-flash-realtime
- qwen3-asr-flash-realtime-2026-02-10
使用场景
- - 实时字幕和标题
- 语音代理双工输入
- 浏览器或终端客户端中的流式语音转文本
前提条件
- - 在环境中设置 DASHSCOPEAPIKEY,或将 dashscopeapikey 添加到 ~/.alibabacloud/credentials 文件中。
- 实时会话通常需要在客户端处理 WebSocket 或流式会话。
标准化接口 (asr.realtime)
请求
- - model (字符串,可选):默认为 qwen3-asr-flash-realtime
- languagehints (字符串数组,可选)
- format (字符串,可选):例如 pcm、wav
- samplerate (整数,可选):例如 16000
- chunk_ms (整数,可选):以毫秒为单位的帧大小
响应
- - text (字符串):识别出的转录片段
- is_final (布尔值):结束标记
- usage (对象,可选)
快速开始
生成请求模板:
bash
python skills/ai/audio/aliyun-qwen-asr-realtime/scripts/preparerealtimeasr_request.py \
--output output/aliyun-qwen-asr-realtime/request.json
操作指南
- - 除非你的客户端技术栈要求其他格式,否则优先使用 16kHz 单声道 PCM。
- 保持数据块足够小,以便获得响应灵敏的部分结果。
- 如果你只有录音文件,请改用 skills/ai/audio/aliyun-qwen-asr/。
参考