Latent Space
Mistral: Voxtral TTS, Forge, Leanstral, & what's next for Mistral 4 — w/ Pavan Kumar Reddy & Guillaume Lample
March 30, 202648 min · 9,502 words
Show notes
Mistral has been on an absolute tear - with frequent successful model launches it is easy to forget that they raised the largest European AI round in history last year. We were long overdue for a Mistral episode, and we were very fortunate to work with Sophia and Howard to catch up with Pavan (Voxtral lead) and Guillaume (Chief Scientist, Co-founder) on the occasion of this week’s Voxtral TTS launch: Mistral can’t directly say it, but the benchmarks do imp…
Highlighted moments
instead of having this autoregressive K step prediction, we have a flow matching model. Instead of modeling this as a discrete token set, we train the codec to be both discrete and continuous to have this flexibility.
“With flow matching, we were able to cut it down significantly. So we are able to do the inference in quad steps or 16 steps, and it works pretty well.”
Transcript
Transcript not available for this episode yet.
More from Latent Space
AI-Native Healthcare: 100M Doctor Visits, 10–20 Hours Saved, Prior Auth in Minutes — Janie Lee & Chai Asawa, Abridge
May 14, 20261h 5m
🔬Doing Vibe Physics — Alex Lupsasca, OpenAI
May 5, 20261h 31m
Physical AI that Moves the World — Qasar Younis & Peter Ludwig, Applied Intuition
Apr 27, 20261h 12m
AIE Europe Debrief + Agent Labs Thesis: Unsupervised Learning x Latent Space Crossover Special (2026)
Apr 23, 202654 min
Shopify’s AI Phase Transition: 2026 Usage Explosion, Unlimited Opus-4.6 Token Budget, Tangle, Tangent, SimGym — with Mikhail Parakhin, Shopify CTO
Apr 22, 20261h 12m