bilibili · Voice
The successor to IndexTTS2, with an unambiguous licence. The cap is Llama-style: written authorisation is needed only if you exceeded 100 million monthly active users in the preceding month or a billion RMB in annual revenue. The card states that the model does not check whether the speaker in your reference clip consented, and that getting that consent is your job.
Summarized from the linked source documents, last checked 25 August 2026. Every claim links to its source; anything unconfirmed is marked unconfirmed.
Commercial use is permitted with a scale cap and some housekeeping. Separate written authorisation is required only above 100 million monthly active users in the preceding calendar month or RMB 1 billion in annual revenue.
The model and its outputs are provided "as is" with no warranty. Prohibited output includes anything unlawful, false information, and discriminatory or privacy-infringing content; high-risk deployment (medical, autonomous driving, military, critical infrastructure) puts regulatory compliance on you. The model card is explicit that it does not verify a reference speaker's consent and that obtaining it is the user's responsibility.
Correction to the shipped catalog: The shipped catalog says "Unknown". It is the bilibili Model Use License Agreement, and its text has been reviewed.
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-index-tts2-5index_tts2There 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-index-tts2-5<models dir>/audiocpp/audiocpp-index-tts2-5/ 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.