Resemble AI / Lightricks · Voice
Heavier than every other voice model here. DramaBox is a fine-tune of Lightricks' LTX-2, so the weights carry the LTX-2 Community License, although Resemble published the model and the inference code is MIT. That licence has the most output-side obligations of any in this catalog.
Summarized from the linked source documents, last checked 25 August 2026. Every claim links to its source; anything unconfirmed is marked unconfirmed.
Free commercial use below $10,000,000 in annual revenue. At or above that you are a “Commercial Entity” under the licence and must obtain a paid commercial licence from Lightricks. If you do not, liquidated damages are set at double the fees owed. The licensor is Lightricks, not Resemble.
Three constraints on what you generate. Machine-generated content must carry an "expressly and intelligibly" stated disclaimer that it is machine generated. Outputs may not be used to train, improve or fine-tune any other machine-learning model, other than LTX-2 derivatives. And every output of the upstream inference path is watermarked with Resemble Perth by default.
Correction to the shipped catalog: The shipped catalog says "Unknown" and lists the vendor as "Unverified". It is the LTX-2 Community License, and the licensor is Lightricks Ltd. DramaBox is an adapter fine-tune of Lightricks' LTX-2, published by Resemble AI.
Based on the licence text as of the date below. Licences change; the links carry the authoritative version.
Transcribed from the shipped catalog, audiocpp_models_catalog.json — that file is authoritative if a number here disagrees with it.
audiocpp-dramaboxdramaboxThere 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.
soundbox model install audiocpp
soundbox pull audiocpp-dramabox<models dir>/audiocpp/audiocpp-dramabox/ rather than in the shared Hugging Face cache, so a download stays scoped to the model you asked for.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.