This connects Claude to Alibaba Cloud's Qwen text-to-speech voice design models, which generate synthetic voices from natural language descriptions instead of requiring pre-recorded samples. You describe the voice you want in plain text and it creates it, which is useful if you need custom TTS voices without hiring voice actors. The skill supports two model variants: a standard one and a realtime version. It's from cinience's alicloud-skills collection, which has seen decent adoption with 391 GitHub stars and 284 installs. The setup requires a virtual environment and SDK installation. All three security audits pass cleanly, so it's vetted for production use if you're already in the Alibaba Cloud ecosystem.
npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-audio-tts-voice-design