RVC (Retrieval-based Voice Conversion)

Paket

Self-hosted voice changer you train on 10 minutes of a voice, for speech or song

Fiyat: Free, open source
Erişim: None, runs locally

Hakkında

MIT-licensed WebUI and CLI from the RVC Project. Train a model of one voice from about 10 minutes of clean audio, then convert recordings, singing or a live microphone into it (about 170 ms end to end). One trained model per voice; runs on NVIDIA, AMD or Intel GPUs or CPU. No pip package.

Neler yapabilirsin

Train a model of one voice and convert recorded speech into that voice
Make AI song covers by converting a sung vocal into another singer's voice
Run a live voice changer on a microphone with the real-time GUI or Windows VST plugin

Başlarken

Install Python 3.12 and the requirements file that matches your GPU
Download the HuBERT and RMVPE base models from Hugging Face into assets/
Train a voice in the WebUI, then convert audio in the WebUI or infer/cli.py

Örnek kod

# Start the WebUI on port 7865 to train a voice model
python webui.py --noautoopen

# Convert a recording with a trained model
python infer/cli.py --model assets/weights/MODEL.pth \
  --input input.wav --output output.wav \
  --pitch 0 --f0-method rmvpe --index-rate 0.75

Ayrıntılar

Barındırma: Kendi bilgisayarında, Kendi sunucunda
Kullanılabildiği yerler: Tüm dünya
MCP sunucusu: Yok