Owen Song · Voice

Inflect Micro v2

Commercial use permittedApache License 2.0

By far the smallest model in the catalog, and the only one that cannot clone a voice: it has one fixed synthetic English voice and takes no reference audio or external model at inference. Apache-2.0, ~400 MB of VRAM. Use it for speech on a machine that cannot run anything else.

owensong/Inflect-Micro-v2 on Hugging Face 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.

Apache License 2.0

Commercial use permitted

Apache-2.0. Commercial use is permitted, with no revenue cap and no research-only carve-out. Keep the copyright and licence notices when you redistribute the weights.

Conditions

The training corpus is not redistributed and the corpus-generation pipeline is closed, so the data provenance is not independently checkable. Third-party components are listed in the project's THIRD_PARTY_NOTICES.md, which was not reviewed here.

What about the audio you generate?

Apache-2.0 claims nothing over output. The card asks that you "disclose synthetic speech where the context could otherwise mislead", and notes the model is not validated for medical, legal, emergency or accessibility-critical use. Advisory, not licence terms.

Correction to the shipped catalog: The shipped catalog says "Unknown" and the vendor "Unverified". It is Apache-2.0, published by Owen Song.

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: Owen Song
Catalog id: audiocpp-inflect-micro-v2
audio.cpp loader family: inflect_v2
Can do: Text to speech
Weights repo: audio-cpp/audio.cpp-gguf
Weights file: Inflect-Micro-v2-GGUF/inflect-micro-v2-orig.gguf
Account needed to download: No
Max clip length: 60s
Sample rate: 44.1kHz mono
Approx. VRAM: 0.4 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-inflect-micro-v2

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-inflect-micro-v2/ 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

One fixed English voice. No reference audio, no cloning, no voice selection.
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.