cosyvoice3-macos
di lhuaizhong
Coding Agents & IDEsSintesi
Local text-to-speech using Alibaba's CosyVoice3 on macOS Apple Silicon.
Descrizione
Cosa fa questa skill
CosyVoice3 runs Alibaba's text-to-speech model locally on macOS Apple Silicon. It supports 9 languages, 18+ Chinese dialects, and zero-shot voice cloning from short audio clips. All inference happens on-device with no network calls required.
Running fully offline on Apple Silicon avoids cloud TTS rate limits, latency, and privacy concerns while still supporting multilingual and dialect output most cloud APIs lack.
Quando usarla
- Clone a speaker's voice from a 5-second recording
- Generate Cantonese or Sichuan dialect speech offline
- Convert English text using a Chinese reference voice
- Add laughter or breathing cues to synthesized audio
- Batch-produce narration WAV files from a script
Esempio di workflow
User asks: generate a WAV file of this Chinese sentence in a cloned voice from reference.wav
- 1
Activate the cosyvoice conda environment
- 2
Load the Fun-CosyVoice3-0.5B model via AutoModel
- 3
Call inference_zero_shot with the target text and reference.wav
- 4
Receive audio chunks from the generator
- 5
Save the output to a WAV file using torchaudio
A WAV file containing the synthesized speech matching the reference speaker's voice
Requisiti
- Conda (Miniconda or Anaconda) installed
- macOS Apple Silicon machine (M1/M2/M3)
- ~5GB free disk space for model files
Installazione
clawhub install lhuaizhong/cosyvoice3-macosEsegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.