jianchang512/clone-voice

A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具,使用你的音色或任意声音来录制音频

Archived
46
/ 100
Emerging

Leverages the Coqui XTTS v2 model for multilingual voice synthesis across 16 languages, supporting both text-to-speech and voice-to-voice conversion with speaker cloning from 5-20 second audio samples. Built as a Flask web application with optional CUDA GPU acceleration for inference, requiring only FFmpeg as an external dependency and offering both standalone precompiled executables and source deployment via Python 3.9-3.11. Integrates with local microphone recording for real-time voice capture and accepts multiple audio formats (MP3/WAV/FLAC) with subtitle file (SRT) import support for batch processing.

8,922 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

8,922

Forks

980

Language

Python

License

Last pushed

Aug 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jianchang512/clone-voice"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.