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

Real-time local transcription on a GGUF runtime path

Unofficial community GGUF conversion for real-time local transcription

Derived from mistralai/Voxtral-Mini-4B-Realtime-2602 and integrated with Openresearchtools-Engine.

Item	Details
Upstream model	mistralai/Voxtral-Mini-4B-Realtime-2602
Conversion source	Derived from the upstream model and converted to GGUF for local runtime use
Conversion script	convert_voxtral_to_gguf.py
License	Apache License 2.0
How to try it
Desktop app example	Try Transcribe Offline to run live (streaming) or static (from audio files) transcriptions with optional diarization on Mac or Windows (Supports Cuda, Vulkan, Metal graphics acceleration or CPU runtime).
Embeddable runtime	Use Openresearchtools-Engine to integrate real-time local transcription into your own application.

Overview

This repository provides an unofficial GGUF conversion derived from mistralai/Voxtral-Mini-4B-Realtime-2602, converted using convert_voxtral_to_gguf.py for real-time local transcription with Openresearchtools-Engine.

The original model is released under Apache License 2.0, and these converted weights are distributed under that same license.

Disclaimer

This is a community conversion and example implementation maintained by OpenResearchTools.

It is not affiliated with, endorsed by, or released by the original model authors or upstream repository owners.

Built for real-time local audio pipelines

• Continuous-session transcription
• Live PCM / streaming-style input
• Embeddable local runtime integration

Related

Need speaker-aware output?
Pair this with openresearchtools/diar_streaming_sortformer_4spk-v2.1-gguf.

Want to test it quickly?
Try Transcribe Offline.

Want to embed it directly?
Use Openresearchtools-Engine.