본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

cosyvoice3-macos

lhuaizhong 제작

Coding Agents & IDEs
395clawskills.sh가 보고한 다운로드 수
1스타
1조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

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

설명

이 스킬이 하는 일

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.

사용 시점

  • 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

예시 워크플로

입력

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

에이전트
  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

출력

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

요구 사항

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

설치

clawhub install lhuaizhong/cosyvoice3-macos

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크