Aratako · Voice

MioCodec voice conversion

Commercial use permittedMIT License

Upstream, MioCodec is a neural audio codec (the 25 Hz tokenizer that MioTTS is built on), not a voice-conversion model in its own right. The shipped catalog drives it through the vc task. The licence is MIT on both code and weights.

Aratako/MioCodec on GitHub 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 has no output clause and claims nothing over what the model generates.

Correction to the shipped catalog: The shipped catalog says "Unknown" and lists the vendor as "Unverified". Both the GitHub project and the weights card are MIT, and the author is Aratako, who also wrote the Irodori and MioTTS entries. Separately: upstream this is a codec, not a voice-conversion model. The repo credits kanade-tokenizer, AliasingFreeNeuralAudioSynthesis and XCodec2 as inspirations; whether any code was carried across from them was not checked.

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: Aratako
Catalog id: audiocpp-miocodec-vc
audio.cpp loader family: miocodec
Can do: Voice conversion
Weights repo: audio-cpp/audio.cpp-gguf
Weights file: MioCodec-25Hz-44.1kHz-v2-GGUF/miocodec-25hz-44khz-v2-q8_0.gguf
Account needed to download: No
Max clip length: 60s
Sample rate: 44.1kHz mono
Approx. VRAM: 0.7 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-miocodec-vc

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-miocodec-vc/ 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

~700 MB of VRAM.
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.