Retrieval-based Voice Conversion WebUI

Local voice conversion: sing or speak, and it comes out in a different voice. Powerful, entirely unsupervised, and the consent problem in this catalog at its sharpest.

At a glance

Where it runs
Self-hostedYou run it on your own machine. Nothing leaves it unless you send it.
Adult content
AllowedAdult content is permitted within the published rules.
Trains on your content
NoYour content is not used to train models.
Status
ActiveMaintained and working today.
Account needed
No
Licence
MIT
Cost
Free and open source.
What it keeps
Local only.

What it takes to run

Graphics memory
4 GB VRAM, 8 GB recommended
System memory
8 GB, 16 GB recommended
Disk
about 15 GB
Runs on
Linux, Windows

Find what fits your machine on the tools page — pick your hardware from the first menu.

RVC converts one voice into another from a comparatively small training set, runs on a consumer graphics card, and asks nothing about whose voice you trained it on. It is genuinely useful — for dubbing, for accessibility, for people who cannot use their own voice — and it is the tool most obviously capable of harm on this site.

We list it because pretending it does not exist helps nobody. Train it on your own voice, or on one you have permission to use, and nothing else.

Worth knowing before you start

What it does

Signs of life

Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.

Last answered
Yes, 3 hours ago Its website responded when we asked.
Stars on GitHub
38,259 5,269 forks.
Last commit
42 days ago2026-08-04 07:47 UTC
Latest release
2.3.260718

Categories

Something here wrong or out of date? Tell us — this page is only worth having if it is right.