qwen-tts-voice-cloning

Community

End-to-end voice cloning on Apple Silicon.

Authorhewliyang
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides an end-to-end workflow to clone a voice using Qwen-TTS on Apple Silicon, encapsulating data collection, cleaning, preparation, training, generation, and evaluation in a reproducible pipeline.

Core Features & Use Cases

  • End-to-end voice cloning pipeline covering data collection (yt-dlp), ASR-based transcription, data preparation, LoRA fine-tuning, and generation.
  • Evaluation with local ASR intelligibility checks plus Gemini-based speaker similarity checks for quality assurance.
  • Supports multiple model variants (base, voice-design, custom-voice) and model sizes (0.6B, 1.7B).

Quick Start

Begin by collecting audio, splitting, preparing data, training a speaker, generating speech, and evaluating results with the CLI.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: qwen-tts-voice-cloning
Download link: https://github.com/hewliyang/qwen-tts/archive/main.zip#qwen-tts-voice-cloning

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.