Mistral Forge is a system that allows enterprises to create frontier-grade AI models based on their proprietary knowledge. It addresses the limitations of existing AI models, which primarily rely on publicly available data, by incorporating internal knowledge such as engineering standards and compliance policies.

The GitHub repository provides a pure C implementation of the inference pipeline for Mistral AI's Voxtral Realtime 4B speech-to-text model, requiring only the C standard library. It features fast MPS inference, a chunked audio processing encoder to manage memory usage, and supports audio input from stdin or live microphone capture.

Voxtral Transcribe 2 features two advanced speech-to-text models, Voxtral Mini Transcribe V2 for batch transcription and Voxtral Realtime for live applications, offering state-of-the-art transcription quality and ultra-low latency. Voxtral Realtime is available as open-weights under the Apache 2.0 license.