Voxtral 3: Mistral speech models and voice agent SDK
Mistral launches Voxtral 3, a family of transcription and text-to-speech models with a voice agent SDK, available through its API with realtime transcription under 500 ms latency.
What the article says
Voxtral 3 brings together transcription models (50+ languages, with diarization and context biasing), a text-to-speech model (35+ languages and 50+ dialects) and a voice agent SDK built on LiveKit. The pipeline listens, reasons, calls tools and replies as one stream, with turns completing in under a second.
Audio can be processed on the EU-hosted API or on the customer’s own infrastructure, and the customer decides whether audio is retained. The models are available now through the Mistral API, with per-minute pricing for transcription and agents.
Read the official article AnnuIA profile
Summary written by AnnuIA in its own words from the official page of Mistral AI. The content and rights belong to the publisher: please read the original article.