This is a Python-based skill that hooks into Alibaba Cloud's Qwen ASR service for transcribing recorded audio files. It handles both short synchronous calls and longer asynchronous jobs, storing transcripts and API responses in a structured output directory. You'd reach for this if you're already in the Alibaba Cloud ecosystem and need non-realtime speech-to-text capabilities. The validation setup is straightforward, just checking that the Python script compiles cleanly. With 285 installs and passing most security audits (Snyk shows a warning), it's getting some real use. Not the flashiest tool, but if you need Qwen ASR integration without writing the API client yourself, it does the job.
npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-audio-asr