Skip to content
TakoAPI
Back to skills

cosyvoice3-macos

by lhuaizhong

Coding Agents & IDEs
395Downloads reported by clawskills.sh
1Stars
1Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Local text-to-speech using Alibaba's CosyVoice3 on macOS Apple Silicon.

Description

What This Skill Does

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.

When to Use It

  • 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

Example Workflow

INPUT

User asks: generate a WAV file of this Chinese sentence in a cloned voice from reference.wav

AGENT
  1. 1

    Activate the cosyvoice conda environment

  2. 2

    Load the Fun-CosyVoice3-0.5B model via AutoModel

  3. 3

    Call inference_zero_shot with the target text and reference.wav

  4. 4

    Receive audio chunks from the generator

  5. 5

    Save the output to a WAV file using torchaudio

OUTPUT

A WAV file containing the synthesized speech matching the reference speaker's voice

Requirements

  • Conda (Miniconda or Anaconda) installed
  • macOS Apple Silicon machine (M1/M2/M3)
  • ~5GB free disk space for model files

Installation

clawhub install lhuaizhong/cosyvoice3-macos

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links