RVC-Project · Voice

RVC voice conversion

Commercial use: conditions applyMIT License

The best-known open voice-conversion stack, and one of the few voice entries with the same permissive licence on code and weights. The upstream project states its base model was trained on the openly licensed VCTK set, so the training-data provenance is documented. The caveat: RVC bundles third-party pieces (ContentVec/HuBERT, RMVPE) whose own licences were not separately verified.

RVC-Project/Retrieval-based-Voice-Conversion-WebUI on GitHub audio.cpp

The licence

Summarized from the linked source documents, last checked 25 August 2026. Every claim links to its source; anything unconfirmed is marked unconfirmed.

MIT License

Commercial use: conditions apply

MIT on the code and MIT tagged on the weights repo; no divergence found. It is shown as conditional for one reason: RVC bundles third-party components (ContentVec/HuBERT, RMVPE) whose upstream licences were not verified, and the MIT grant on RVC does not speak for them.

Conditions

The bundled ContentVec/HuBERT and RMVPE components have their own upstream licences, which were not checked here. Check them before shipping.

What about the audio you generate?

MIT has no output clause and claims nothing over what the model generates.

Correction to the shipped catalog: The shipped catalog says "Unknown". Both the code and the weights are MIT. The remaining uncertainty is about RVC's dependencies, not about RVC.

Based on the licence text as of the date below. Licences change; the links carry the authoritative version.

Specs

Transcribed from the shipped catalog, audiocpp_models_catalog.json — that file is authoritative if a number here disagrees with it.

Vendor: RVC-Project
Catalog id: audiocpp-rvc
audio.cpp loader family: rvc
Can do: Voice conversion
Weights repo: audio-cpp/audio.cpp-gguf
Weights file: RVC-GGUF/rvc-f16.gguf
Account needed to download: No
Max clip length: 60s
Sample rate: 44.1kHz mono
Approx. VRAM: 3.2 GB
In the picker by default: No — opt in from Settings
Run end-to-end here: No — catalogued, not tested here

Getting it

There is no per-model install. One native binary runs all of these, so getting a model is a download of its weights and nothing else — no virtualenv, no torch pin, no CUDA wheel to match against your driver.

From the CLI

soundbox model install audiocpp
soundbox pull audiocpp-rvc

The binary is fetched from audio.cpp's GitHub releases the first time you ask for it and cached under your own data directory. Soundbox ships no native binaries and vendors none.
Weights land in <models dir>/audiocpp/audiocpp-rvc/ rather than in the shared Hugging Face cache, so a download stays scoped to the model you asked for.
This one is opt-in: switch it on in the Models page's “Enable more models” section before it appears in the picker.

Worth knowing

Voice conversion, not text-to-speech.
Opt-in and untested here.

Sources

Primary sources: the model's own repository, the project it came from, and the conversion audio.cpp actually downloads. Never invented — an entry with nothing findable says so instead.

Licence details on these pages are summaries of the linked source documents, last checked 25 August 2026. They are not legal advice, and Soundbox is not affiliated with any model's authors — weights download from Hugging Face under the user's own account and terms. Company and model names identify whose work it is, and belong to their owners. The linked licence text is authoritative; commercial use should be checked against it, per model, before anything ships.