İçeriğe geç
TakoAPI
Becerilere dön

cosyvoice3-macos

lhuaizhong tarafından

Coding Agents & IDEs
395İndirme sayıları clawskills.sh tarafından bildirilir
1Yıldızlar
1Görüntülenmeler
0 beğeniBu beceriyi beğenmek için giriş yapın
—Henüz değerlendirilmedi
Puanınız

Özet

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

Açıklama

Bu Beceri Ne Yapar

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.

Ne Zaman Kullanılır

  • 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

Örnek İş Akışı

GİRİŞ

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

AJAN
  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

ÇIKIŞ

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

Gereksinimler

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

Kurulum

clawhub install lhuaizhong/cosyvoice3-macos

CLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.

Bağlantılar