Pass IndexThe State of AISign in

Voxtral-Mini-4B-Realtime-2602

Built with a natively streaming architecture and a custom causal audio encoder - it allows configurable transcription delays (240ms to 2.4s), enabling users to balance latency and accuracy based on their needs.

audio → text · made by Mistral AI

Sold by

Nobody in the catalogue publishes a price for this yet.

About

Voxtral-Mini-4B-Realtime-2602 — a text model from Mistral AI.

It takes audio and returns text. It was published in January 2026. The catalogue files it under transcribe. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.

Every current figure

Maker
Mistral AI
Register
model
Takes
audio
Returns
text
Published
January 2026
Parameters
4.4 billion · read from its own weights
Licence
apache-2.0

Known as 1 name

mistralai/Voxtral-Mini-4B-Realtime-2602