Menu
Text to speech with voice clone using Qwen3-TTS.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | qwen-tts |
| description | Text to speech with voice clone using Qwen3-TTS. |
| metadata | {"tags":["aigc","tts","speech","voice","qwen3"],"platforms":["linux"]} |
tldr: Use uv run ${SKILL_DIR}/scripts/generate_voice.py to generate speech audio with voice clone.
--text "the text you want to synthesize" --ref-audio "/abs/path/to/ref/audio.wav" --ref-text "Ref Audio Transcript" --output "output.wav"
--help shows the full usage.--ref-text is optional. If omitted, it defaults to the ref audio filename.