Amphion · Voice

Vevo2

Non-commercial onlyCC-BY-NC-ND-4.0 (weights) / MIT (code)

Amphion's toolkit is MIT, and that is the licence a quick search finds. The Vevo2 checkpoints are published CC-BY-NC-ND-4.0: non-commercial, attribution required, and, read strictly, no distributing derivatives, which would cover redistributing a fine-tune. The checkpoints' licence is the binding one; the MIT code licence does not change it.

RMSnow/Vevo2 on Hugging Face 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.

CC-BY-NC-ND-4.0 (weights) / MIT (code)

Non-commercial only

The weights are CC-BY-NC-ND-4.0: non-commercial only, attribution required, and no derivative works distributed. The Amphion code around them is MIT, which is a different thing and does not loosen the weights' terms.

Conditions

Non-commercial use only.
Attribution required.
No-derivatives: read strictly, this bars distributing a fine-tune or other modified checkpoint.

What about the audio you generate?

Plain CC-BY-NC-ND has no acceptable-use policy and claims no rights over model output. No consent clause or output statement was found on either the Amphion README or the weights card; both were checked.

Correction to the shipped catalog: The shipped catalog says "Unknown" and "conditional". These weights are non-commercial, which is stricter than conditional. The shipped catalog also listed Vevo2 as a music generator at one point; the 0.6.1 loader registry says it registers tts, vc, s2s and svc and no gen task at all, which is why it appears here as a voice model.

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: Amphion
Catalog id: audiocpp-vevo2
audio.cpp loader family: vevo2
Can do: Text to speech, Voice conversion
Weights repo: audio-cpp/audio.cpp-gguf
Weights file: Vevo2-GGUF/vevo2-q8_0.gguf
Account needed to download: No
Max clip length: 60s
Sample rate: 44.1kHz mono
Approx. VRAM: 4.0 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-vevo2

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-vevo2/ 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

This entry drives it as text-to-speech. The vevo2 family also registers voice conversion, speech-to-speech and singing voice conversion.
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.