Mistral Releases Voxtral 3 Speech Model with Real-Time Speaker Diarization and Turn Detection
Mistral has released Voxtral 3, comprising the Transcribe and Speech models, to power its new voice agents API. Co-founder Arthur Mensch added that Voxtral can perform speaker diarization and end-of-turn detection on the fly, and can be deployed either on your own infrastructure or via Mistral's cloud service.
Why read this
AI score 60
Mistral's co-founder added details on Voxtral 3's speaker diarization and end-of-turn detection capabilities, noting it can be deployed locally or in the cloud.
Topics
View original postIntroducing Voxtral 3: state-of-the-art Transcribe and Speech models powering Mistral’s new voice agents API. 🧵 https://t.co/YA9HNVfq0u
View original
Introducing Voxtral 3: state-of-the-art Transcribe and Speech models powering Mistral’s new voice agents API. 🧵 https://t.co/YA9HNVfq0u
Body
Voxtral diarizes and detects end-of-turn on the fly. Runs on your infra or on ours (the one in the train station)