Model · Voice and speech

RVC (Retrieval-based Voice Conversion)

Free, downloadable software that makes a recording or live voice sound like another voice. You train a voice from about 10 minutes of clean speech, then convert audio through a web page it runs on your own computer. Needs technical setup.

Go to RVC (Retrieval-based Voice Conversion)’s website

At a glance

Open or closed: Fully open
Weights and code downloadable under a standard open licence
Code is MIT. Pretrained base models (on Hugging Face, lj1995/VoiceConversionWebUI) have no separate licence stated; README says they were trained on the open VCTK dataset.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Licence: MIT (Permissive (e.g. Apache 2.0, MIT))
Repo listed as MIT; a combined licence file covers referenced libraries, contents not read.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Can I sell what I make?: Yes
Follows from the MIT licence; README says the base model has no copyright concerns. Rights in a voice you copy are a separate matter the README does not address.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost: Free option: Free to download; you pay for your own hardware
Plans below.
How you use it: On your own computer
Python 3.12; Ubuntu 24.04 recommended. macOS not mentioned. Runs a local web UI.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
Python install and model training required.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: RVC-Project (open-source community)
Published by the RVC-Project GitHub organisation; no company or country stated.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
No maintenance notice; README says an RVCv3 base model is coming.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

A voice or speech, my voice sounding like someone else (main use)
A voice or speech, a copy of my own voice

audio to audio

Main README is in Chinese; read via translation. Voice training from about 10 minutes of speech. Also bundles vocal separation as a preparation step (not listed as a task).

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Rights and safety

Real faces and voices: Copies a real voice (train a voice model from recordings), no consent step
Any recordings can be used for training; README says nothing about consent.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Where you can run it

Hugging Face

Other options for “A voice or speech, my voice sounding like someone else”

Akool, Filmora, Kits AI, Krisp, Magic Hour, Musicfy, MyEdit, Respeecher, Voice-Swap, Voicemod

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.