Mistral AI launches Voxtral, a new open-source voice model family. It aims to challenge OpenAI's Whisper and Google's Gemini ...

This paper proposes a novel collaborative dysarthric speech recognition system designed to convert dysarthric speech into non-dysarthric speech to enhance the robustness of automatic speech ...

Mistral's open-source speech model Voxtral can recognize multiple languages, understand spoken instructions and also offer enterprise security.