RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Health v2 · maintenance only

Adoption not part of the score

37845 stars · 5239 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A WebUI-based framework for training and running retrieval-based voice conversion (RVC) models, letting users clone a voice timbre from as little as 10 minutes of clean speech. It includes training and inference interfaces, a real-time voice changer with ~90-170ms latency, and vocal/instrumental separation via MSS models.

Use cases

• train an AI voice conversion model from 10 minutes of audio
• convert my voice to another voice in real time
• make an AI singing voice cover of a song
• clone a voice timbre from short recordings
• separate vocals from a song's instrumental
• run a low-latency voice changer for streaming or calls

When to choose

• you want high-quality voice conversion trained on very little data
• you need a GUI for both training and real-time inference
• you want to avoid timbre leakage via retrieval-based feature replacement
• you have a modest GPU or even CPU/AMD/Intel fallback options

When to avoid

• you need text-to-speech synthesis rather than voice-to-speech conversion
• you want a production API service rather than a local WebUI
• you have no GPU and need very fast batch inference
• you need fully automated headless pipelines with no GUI

Facets

application · maturity active

machine-learning audio-processing speech-recognition llm-training gui machine-learning deep-learning media python windows cross-platform voice-conversion voice-cloning ai-singer realtime-voice-changer webui so-vits-svc vocal-separation audio linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="RVC-Project/Retrieval-based-Voice-Conversion-WebUI")