What it is
VibeVoice-ASR is a speech-recognition model that turns recorded speech into text, published by Microsoft on Hugging Face on 21 January 2026. It has about 8.7 billion parameters.
Its card lists the licence as MIT. In short, the licence allows commercial use, modification and redistribution as long as the copyright notice is kept.
Hugging Face counted about 723,068 downloads of it in the 30 days before we checked (7 Oct 2026), and 1,302 people have liked it there.
The card lists 51 languages: en, zh, es, pt, de, ja, ko, fr, ru, id, sv, it and 39 more (ISO codes as given on the card).