Pass IndexThe State of AISign in

voz

On-device speech recognition: transcripts with word-level timestamps, 25 languages.

audio → text · made by Desert Ant Labs

Sold by

Nobody in the catalogue publishes a price for this yet.

About

voz — a text model from Desert Ant Labs.

It takes audio and returns text. It was published in August 2026. The catalogue files it under transcribe. Its weights are published under the other licence, which attaches conditions the plain open licences do not.

Every current figure

Maker
Desert Ant Labs
Register
model
Takes
audio
Returns
text
Published
August 2026
Licence
other

Known as 1 name

desert-ant-labs/voz