Speaking of Voxtral
Voxtral TTS: A frontier, open-weights text-to-speech model that’s fast, instantly adaptable, and produces lifelike speech for voice agents.
Get smart on it
Mistral AI has released Voxtral TTS, a text-to-speech model designed to generate realistic, emotionally expressive speech in nine languages while remaining compact at 4 billion parameters. The model can adapt to new voices with minimal reference audio and demonstrates low latency for real-time voice agent applications. According to human evaluations by native speakers, Voxtral TTS achieves superior naturalness compared to some competing systems while maintaining similar response times, making it suitable for enterprise voice workflows that require natural-sounding and culturally nuanced speech generation.
Related news
Mistral OCR 4 Brings Citation-Ready Structured Output to RAG, Agentic, and Enterprise Search Pipelines
Today, Mistral AI released OCR 4, its latest document-understanding model. This new release adds bounding boxes, block classification, and inline confidence scores alongside extracted text. It supports 170 languages across 10 language groups and runs in a single container for fully self-hosted deployments. OCR 4 also serves as an ingestion component for enterprise search, RAG, and domain-specific retrieval pipelines. TL;DR OCR 4 returns bounding boxes, typed-block labels, and per-word c
Datalab Releases lift: A 9B Open-Weights Vision Model That Extracts Structured JSON From PDFs Using Schemas
Datalab has released lift, a 9B open-weights vision model for structured extraction. You pass it a JSON schema, and it returns a JSON object that matches. The model reads PDFs and images directly, then decodes against your schema. This is Datalab’s first model built purely for extraction. The team already ships open-source OCR tools: chandra, marker, and surya. lift extends that work into schema-driven field extraction. lift scores 90.2% field accuracy on Datalab’s 225-documen
