Lewati ke konten
TakoAPI
Kembali ke skill

cosyvoice3-macos

oleh lhuaizhong

Coding Agents & IDEs
395Unduhan dilaporkan oleh clawskills.sh
1Bintang
1Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

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

Deskripsi

Apa yang Dilakukan Skill Ini

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.

Kapan Menggunakannya

  • 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

Contoh Alur Kerja

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

Persyaratan

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

Instalasi

clawhub install lhuaizhong/cosyvoice3-macos

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan