Resemble AI · Voice

Chatterbox

Commercial use permittedMIT License

MIT, ungated, no revenue threshold, no research carve-out. Resemble embeds its Perth neural watermark in everything the model generates, and says the watermark survives MP3 compression and editing. That is a design decision, not a licence term. It matters if the output is meant to be indistinguishable from a recording.

ResembleAI/chatterbox 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.

MIT License

Commercial use permitted

MIT. Commercial use permitted, no threshold, no field-of-use restriction; keep the copyright notice when redistributing the weights.

What about the audio you generate?

MIT claims nothing over output. But every generation is watermarked with Resemble's Perth neural watermark, which the project says survives compression and editing.

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: Resemble AI
Catalog id: audiocpp-chatterbox
audio.cpp loader family: chatterbox
Can do: Text to speech
Weights repo: audio-cpp/audio.cpp-gguf
Weights file: Chatterbox-GGUF/chatterbox-q8_0.gguf
Account needed to download: No
Max clip length: 60s
Sample rate: 44.1kHz mono
Approx. VRAM: 3.0 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-chatterbox

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-chatterbox/ 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. The numbers in the specs table come from the catalog and were not measured.
The card's only conduct guidance is an informal "don't use this model to do bad things". That is neither a licence term nor a consent requirement. Making sure you have the right to use any reference audio is your responsibility.

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.