#3434th of 67 in VoiceFor voice, speech and music
retrieval-based-voice-conversion-webui
Web UI for training and running retrieval-based voice conversion models
- Stars
- 39k
- License
- MIT
- Last commit
- Aug 2026
- Last release
- Jul 2026
- Language
- Python
34,667 on 10 Apr 202638,998 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Gradio web UI for training RVC voice models and converting speech or singing to a target voice. It replaces input features with top-1 retrieved training-set features to reduce timbre leakage, and uses RMVPE for pitch extraction. It includes a real-time voice changer GUI, vocal/accompaniment separation via pymss/MSST, and checkpoint merging. The README recommends at least 10 minutes of clean voice data.
Who it is for: Hobbyists and developers training voice-conversion or AI singer models
Strengths
- Trains usable models from about 10 minutes of low-noise audio, per the README
- Separate real-time GUI: 170 ms end-to-end latency, 90 ms with ASIO devices
- Includes vocal separation (pymss/MSST) and ckpt-merge in the same tool
- CPU, DirectML (Windows) and CUDA 11.8/12.8 install paths
Weaknesses
- Manual setup: Python 3.12 venv, separate Torch install, and several model downloads
- No Docker or compose files in the repo
- Main README is in Chinese; English docs live in docs/en
- Low latency depends on ASIO hardware drivers; RVCv3 base models are not released yet
What it needs
- GPU optional
- Needs Python 3.12, PyTorch, FFmpeg, Gradio, Hugging Face model weights (hubert_base, rmvpe, pretrained)
- Models: RVC v1/v2 .pth, RMVPE, HuBERT/ContentVec, FAISS .index, pymss/MSST
- port 7865
Quick answers
Is retrieval-based-voice-conversion-webui open source?
Yes. Its code is on GitHub under the MIT license.
Does retrieval-based-voice-conversion-webui need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |