Qwencloud Audio Tts

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.

skills.sh installs: 1.7K
GitHub stars: 44
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add qwencloud/qwencloud-ai --skill qwencloud-audio-tts --agent claude-code

Installs into .claude/skills of the current project.

Files

Qwen Audio TTS (Text-to-Speech)

Synthesize natural speech from text using Qwen TTS models. This skill is part of qwencloud/qwencloud-ai.

Skill directory

Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.

Location	Purpose
`scripts/tts.py`	Qwen TTS / Qwen Audio TTS (HTTP and WebSocket); current compatibility and defaults are in the model catalog below
`scripts/tts_cosyvoice.py`	CosyVoice (WebSocket API) — requires `dashscope` SDK; current compatibility and defaults are in the model catalog below
`references/cosyvoice-guide.md`	CosyVoice setup, voices, examples, errors
`references/execution-guide.md`	Fallback: curl (standard, instruct, streaming), code generation
`references/prompt-guide.md`	Text formatting for speech, instructions templates, voice selection
`references/api-guide.md`	API supplement
`references/sources.md`	Official documentation URLs