abus-aikorea/voice-pro

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

52
/ 100
Established

Provides integrated speech-to-text pipeline combining multiple Whisper variants (Faster-Whisper, WhisperX) for optimized accuracy and timing precision, then routes output through Deep-Translator for 100+ language support. Built on Gradio with CUDA acceleration for Windows/NVIDIA GPU environments, orchestrating Demucs/MDX-Net vocal isolation, RVC voice conversion, and multiple TTS engines (kokoro, Edge-TTS, CosyVoice) into a unified multimedia dubbing workflow without external API dependencies.

6,366 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

6,366

Forks

687

Language

Python

License

GPL-3.0

Last pushed

Dec 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/abus-aikorea/voice-pro"

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