qianwen-audio-tts
qianwen-aiTurn your text into natural Qwen speech.
speech synthesis
What it does
Synthesizes text into natural speech audio using Qwen TTS models.
When to use it
Use when the user wants text converted into speech, narration, voiceovers, or other audio output.
How to use it
Give it text to synthesize; it returns generated audio and response data in an output directory.
What you provide
- text to synthesize
Uses
Access · 6
This skill
<repo>/.agents/state.json
Overwrites update prompt state (irreversible)
Qwen TTS API
Sends text to Qwen TTS
QianWen Voice Cloning
Uploads a voice sample
Qwen audio TTS model catalogs
Reads current model catalogs
Good to know
- cannot be undone: <repo>/.agents/state.json
- advertises something the task does not need
What you need · 3
The default bundled TTS script requires Python 3.9 or newer.
The TTS path reads either API-key name configured in a .env file.
The dashscope SDK is required when using the optional CosyVoice path.
About this skill
- Visibility
- Public
- Repository
- qianwen-ai/qianwen-ai
- Created
- Oct 8, 2026
- Updated
- Oct 8, 2026
- Files
- 15