Plachtaa (Seed-VC) · Voice

Seed-VC voice conversion

Commercial use: conditions applyGNU General Public License v3.0

The only licence in this catalog that can apply to your own software. GPL-3.0 permits commercial use, but distributing a derivative work or an application linked against it obliges you to release the corresponding source under GPL-3.0. Running it internally or behind a hosted service is fine, because this is GPL and not AGPL. Check the obligations before you ship it inside a closed-source product.

The licence

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

GNU General Public License v3.0

Commercial use: conditions apply

GPL-3.0 on both the code and the weights repo. Commercial use is permitted. The copyleft obligation is the main condition: distribute a derivative or an application built on it and you must offer the corresponding source under GPL-3.0.

Conditions

  • Strong copyleft: distributing a derivative work triggers the source-release obligation.
  • This is GPL-3.0, not AGPL, so a hosted service you do not distribute does not trigger it.
  • The obligation attaches to your software, not to the audio. See the output note.

What about the audio you generate?

GPL does not claim rights over the output of a program, and there is no output clause here. Converting a voice does not put your audio under the GPL; linking your application against the model might put your application under it.

Correction to the shipped catalog: The shipped catalog says "Unknown". It is GPL-3.0, on both the code and the weights repo. It is the only copyleft licence in this catalog, and it matters most to anyone embedding Soundbox in other software.

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
Plachtaa (Seed-VC)
Catalog id
audiocpp-seed-vc
audio.cpp loader family
seed_vc
Can do
Voice conversion
Weights file
SeedVC-MLX-GGUF/seed-vc-mlx-q8_0.gguf
Account needed to download
No
Max clip length
60s
Sample rate
44.1kHz mono
Approx. VRAM
2.5 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-seed-vc
  • 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-seed-vc/ 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: it takes source audio and a reference voice.
  • 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.