alicloud-ai-audio-asr

Category: provider Pass criteria: command exits 0 and output/alicloud-ai-audio-asr/validate.txt is generated. Use Qwen ASR for recorded audio transcription (non-realtime), including short audio sync calls and long audio async jobs. Use one of these exact model strings: Selection guidance: Sync transcription (OpenAI-compatible protocol): Async long-file transcription (DashScope protocol): Poll task result: Use the bundled script for URL/local-file input and optional async polling: Long-file mode: - Store transcripts and API responses under output/alicloud-ai-audio-asr/ . - Keep one command log or sample response per run. - qwen3-asr-flash - qwen-audio-asr - qwen3-asr-flash-filetrans - Use qwen3-asr-flash or qwen-audio-asr for short/normal recordings (sync). - Use qwen3-asr-flash-filetrans for long-file transcription (async task workflow). - Install SDK dependencies (script uses Python stdlib only): - Set DASHSCOPE_API_KEY in environment, or add dashscope_api_key to ~/.alibabacloud/credentials . - audio (string, required): public URL or local file path.