Soundbox

rednote HiLab · Voice

Dots TTS Edit

Terms unconfirmedUnresolved: declared "other", unnamed

The dots.tts variant with no confirmed licence. SOAR and MF are Apache-2.0 on their own repos, and that is not assumed to carry over. Edit declares “other” with no licence name, no licence link and no LICENSE file, and lives under a different Hugging Face organisation from the other two. The upstream README says dots.tts checkpoints are Apache-2.0 and does not carve Edit out, so Apache-2.0 is the likely intent. The repo itself contradicts it.

dots-studio/dots.tts.edit on Hugging Faceaudio.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.

Unresolved: declared "other", unnamed

Terms unconfirmed

This model's licence could not be confirmed. Its Hugging Face repo declares “other” with no licence name and no licence link, and there is no LICENSE file in it (the repo's files were enumerated and the licence path returns nothing). The card only says to see the repository licence metadata, which declares nothing.

Conditions

  • The upstream dots.tts README states that code and released checkpoints are Apache-2.0, without carving out Edit. That makes Apache-2.0 the likely intent, but the repo's metadata says “other”. This page does not resolve that contradiction on the publisher's behalf.
  • Ask rednote HiLab before any commercial use. If you want this family with terms you can read, use SOAR or MF.

What about the audio you generate?

The card asks users not to impersonate people, mislead listeners, violate consent or create unlawful content, and to disclose synthetic or edited audio. Since the licence cannot be identified, whether any of that is contractual cannot be stated.

Correction to the shipped catalog: The shipped catalog says "Unknown", and that is still right. audio.cpp's conversion table labels this package Apache-2.0, matching the other two variants, but the weights repo declares "other" and names no licence at all. Edit lives under the dots-studio organisation on Hugging Face, not rednote-hilab.

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
rednote HiLab
Catalog id
audiocpp-dots-tts-edit
audio.cpp loader family
dots_tts
Can do
Text to speech
Weights repo
audio-cpp/audio.cpp-gguf
Weights file
DotTTS-Edit-GGUF/dots-tts-edit-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-dots-tts-edit
  • 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-dots-tts-edit/ 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

  • The only dots.tts variant whose licence could not be established.
  • 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.

Related models

Same loader family (dots_tts)

Other voice models