Zum Inhalt springen
TakoAPI
Zurück zu den Skills

cosyvoice3-macos

von lhuaizhong

Coding Agents & IDEs
395Downloadzahlen laut clawskills.sh
1Sterne
1Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

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

Beschreibung

Was dieser Skill macht

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.

Wann du ihn einsetzt

  • 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

Beispiel-Workflow

EINGABE

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

AUSGABE

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

Voraussetzungen

  • 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

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links