JackismyShephard/ultimate-rvc

An app for creating audio-based content such as song covers and speech using Retrieval-based Voice Conversion.

55
/ 100
Established

Supports TTS synthesis, custom voice model training, and intermediate audio caching to reduce inference time across pipeline steps. Built with Gradio 5 and Python 3.13, it offers modular "multi-step" generation tabs for isolating individual processing stages (vocal extraction, pitch conversion, etc.) and includes multiple pitch extraction methods (FCPE) with post-processing options like autotuning and noise reduction. Available as a PyPI package, deployable locally on Windows/Linux or via Google Colab for GPU-constrained environments.

264 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

264

Forks

64

Language

Python

License

MIT

Last pushed

Dec 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/JackismyShephard/ultimate-rvc"

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