bilibili · Voice

IndexTTS2

Terms unconfirmedbilibili Model Use License Agreement (inferred)

Its Hugging Face repo has no licence field and its card has no licence section. The upstream GitHub project now carries the bilibili Model Use License Agreement. Blog posts calling IndexTTS2 Apache-2.0 appear to describe the older v1 era. No authoritative page resolves this, so this page points to the more restrictive reading.

The licence

Summarized from the linked source documents, last checked 25 August 2026. Every claim links to its source; anything unconfirmed is marked unconfirmed.

bilibili Model Use License Agreement (inferred)

Terms unconfirmed

Which licence governs these weights could not be confirmed. The Hugging Face repo carries no licence metadata and no licence section. The upstream repository's current LICENSE is the bilibili Model Use License Agreement, and audio.cpp's conversion table also labels this package that way. That is the most likely answer, but nothing on the weights repo itself says so.

Conditions

  • If the bilibili agreement does govern, its conditions are the ones described on the IndexTTS2.5 page: a scale cap, notice retention, and a no-endorsement statement for modifications.
  • Widely repeated claims that IndexTTS2 is Apache-2.0 are not supported by any current authoritative page that could be reached.

What about the audio you generate?

No output clause could be confirmed for this specific model. If the bilibili agreement applies, its terms about outputs and high-risk use apply with it.

Correction to the shipped catalog: The shipped catalog says "Unknown", and that is still accurate for this repo. The details are now documented: the weights repo declares nothing, and the project it came from declares the bilibili agreement. Prefer IndexTTS2.5, whose licence is unambiguous.

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
bilibili
Catalog id
audiocpp-index-tts2
audio.cpp loader family
index_tts2
Can do
Text to speech
Weights file
IndexTTS2-GGUF/index-tts2-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-index-tts2
  • 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-index-tts2/ 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.
  • For this family with a readable licence, use IndexTTS2.5.

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.