TrevorS/voxtral-mini-realtime-rs

Streaming speech recognition running natively and in the browser. A pure Rust implementation of Mistral's Voxtral Mini 4B Realtime model using the Burn ML framework.

54
/ 100
Established

This project helps anyone who needs to quickly convert spoken words into text or generate speech from written text, directly on their computer or even in a web browser. You provide audio recordings or live microphone input to get transcribed text, or give it text to generate natural-sounding spoken audio in various voices. It's designed for individuals and applications that require fast, client-side speech processing.

710 stars. Actively maintained with 32 commits in the last 30 days.

Use this if you need a high-performance speech-to-text or text-to-speech solution that runs locally on your machine or directly within a web browser, without relying on cloud services.

Not ideal if you require highly specialized, domain-specific transcription accuracy that might benefit from more extensive training data or custom models.

audio-transcription voice-assistants accessibility speech-synthesis real-time-communication
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 13 / 25

How are scores calculated?

Stars

710

Forks

33

Language

Rust

License

Apache-2.0

Last pushed

Feb 12, 2026

Commits (30d)

32

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/TrevorS/voxtral-mini-realtime-rs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.