Mistral: Voxtral TTS, Forge, Leanstral, & Mistral 4 — w/ Pavan Kumar Reddy & Guillaume Lample
Mistral is one of the world's leading frontier model labs, and has just raised $900m to build their European data center hub. Last year marked their first ventures into multimodal models, with Pixtral and then Voxtral in 2025, ending the year with a monster €1.7B fundraise at a €10B premoney (https://mistral.ai/news/mistral-ai-raises-1-7-b-to-accelerate-technological-progress-with-ai) - the largest European AI fundraise ever.
This week they launched Voxtral TTS (https://mistral.ai/news/voxtral-tts) and it is filling in yet another important gap in the open source frontier for all modalities o…
Watch on YouTube ↗
(saves to browser)
Chapters (25)
Welcome and Guests
0:22
Announcing Voxtral TTS
1:41
Architecture and Codec
2:53
Understanding vs Generation
4:50
Flow Matching Explained
7:25
Real Time Voice Agents
13:40
Efficiency and Model Strategy
14:53
Voice Agents Vision
17:56
Enterprise Deployment and Forge
23:39
Fine Tuning and Personalization
25:22
Enterprise Voice Personalization
26:09
Long Form Speech Models
26:58
Real Time Encoder Advances
27:45
Scaling Context for TTS
28:53
What Makes Small Models
30:23
Merging Capabilities Strategy
32:04
Voice Meets Video Latency
33:05
Open Source Mission
35:51
Lean and Formal Proofs
38:40
Reasoning Transfer and Agents
40:25
Next Training Frontiers
42:20
Hiring and Global Teams
43:05
AI for Science Partnerships
44:19
Forward Deployed Engineering
47:01
Real World Evals and Wrap Up
DeepCamp AI