Voxtral 3

Mistral has released Voxtral 3, a voice agent SDK with advanced speech-to-text and text-to-speech models supporting 50+ languages for real-time, multi-step conversations. The system combines accurate transcription, natural speech synthesis with emotional expression, and tool integration for workflow automation across applications like contact centers and virtual assistants. Available through Mistral's EU-hosted API or for self-deployment, it prioritizes data sovereignty and low-latency, human-like interactions.