In simple English
This tool lets you take someone else's voice and make any recorded song or speech sound like them. You collect ten minutes of clear audio of the target person and feed it into the program. It trains a model on your computer so you can convert audio files or speak into a microphone in real time. The software runs entirely on your own hardware, so nothing is sent to the cloud. It is free to use, but you need a powerful graphics card to train and run the models quickly.
What it is
Retrieval-based-Voice-Conversion-WebUI is an open-source voice cloning framework with a graphical web interface. It combines a feature retrieval system with modern neural audio synthesis to turn one voice into another.
What it is good for
Content creators, game modders and hobbyists who want to produce custom voiceovers or experiment with neural audio conversion using their own hardware.
- Trains usable voice models with as little as ten minutes of audio.
- Includes a local web interface for easy file conversion and training.
- Supports real-time voice changing with low audio latency on compatible hardware.
- Requires an NVIDIA graphics card with enough memory for practical use.
- Setup involves installing specific Python environments and downloading large model weights.
- Training models takes time and trial-and-error to get clean results.
commercial voice cloning services
FFmpeg
- fishaudio/fish-speech33k stars
Another open-source text-to-speech and voice cloning project that runs locally.
- jaywalnut310/vits7.9k stars
A core neural speech synthesis model that provides the foundation for many voice conversion tools.
- shaka-project/shaka-packager2.6k stars
Cuts a video file into the pieces and index files that a browser needs in order to stream it.
- mpv-player/mpv38k stars
A command-line media player that handles most audio, video and subtitle formats and can be driven entirely from scripts.
- snapcast/snapcast8.0k stars
A server and clients that play one audio stream in several rooms, kept in time with each other.
git clone https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI cd Retrieval-based-Voice-Conversion-WebUI python3.12 -m venv .venv source .venv/bin/activate python -m pip install --upgrade pip setuptools wheel pip install -r requirments_cpu_py312.txt python webui.py