OpenBMB · Voice

VoxCPM2

Commercial use permittedApache License 2.0

One of the few entries whose model card states in plain words that it is free for commercial use. The card's prohibitions (no impersonation, no fraud, no disinformation, label AI-generated content) are in the card text, not in Apache-2.0. They are norms the publisher asks you to follow, not licence conditions.

openbmb/VoxCPM2 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.

Apache License 2.0

Commercial use permitted

Apache-2.0. Commercial use is permitted, with no revenue cap and no research-only carve-out. Keep the copyright and licence notices when you redistribute the weights.

What about the audio you generate?

Apache-2.0 claims nothing over output. The card adds advisory guidance: "strictly forbidden to use for impersonation, fraud, or disinformation" and "AI-generated content should be clearly labeled". That is the publisher's norm, not an enforceable licence condition. There is no mechanism verifying consent for reference audio.

Correction to the shipped catalog: The shipped catalog says "Unknown". Weights and code are both Apache-2.0.

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: OpenBMB
Catalog id: audiocpp-voxcpm2
audio.cpp loader family: voxcpm2
Can do: Text to speech
Weights repo: audio-cpp/audio.cpp-gguf
Weights file: VoxCPM2-GGUF/voxcpm2-q8_0.gguf
Account needed to download: No
Max clip length: 60s
Sample rate: 44.1kHz mono
Approx. VRAM: 3.6 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-voxcpm2

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-voxcpm2/ 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

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.