Converts text to speech using QwenCloud's Qwen TTS and CosyVoice models via Python scripts or curl. You get qwen3-tts-flash for standard narration, qwen3-tts-instruct-flash for tone control, and the CosyVoice models for higher quality output. Includes system voices like Cherry, Ethan, and Serena. The skill handles API key detection (warns you if you're using an incompatible Coding Plan key), comes with reference docs for WebSocket setup and prompt formatting, and enforces credential safety by design. Works with Python 3.9+ stdlib only, no dependencies. If you need voiceovers, audio narration, or TTS integration and you're already in the QwenCloud ecosystem, this does the job without ceremony.
npx skills add https://github.com/qwencloud/qwencloud-ai --skill qwencloud-audio-tts