antirez/voxtral.c

Pure C inference of Mistral Voxtral Realtime 4B speech to text model

C1.7K stars121 forks

What it does

Voxtral is a pure C implementation of Mistral AI's Voxtral Realtime 4B speech-to-text model, designed for efficient audio transcription with zero external dependencies. Its lightweight nature and real-time capabilities make it ideal for developers looking to integrate speech recognition into their applications.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-02-21

Creator kit

Hook

Transform your audio into text in real-time with this lightweight C implementation of the Voxtral model!

Content angles

Create a tutorial on setting up and using Voxtral for live audio transcription.
Compare the performance of Voxtral with other speech-to-text solutions in a blog post.
Develop a video series showcasing different use cases for Voxtral in real-world applications.

Who should care

Developers and content creators interested in speech recognition technology.