Notion's AI Meeting Notes run on Baseten, and Baseten's knowledge base runs on Notion. Our teams have been working together closely to push the frontier on both fronts. For AI Meeting Notes, our voice engineers built the fastest, highest-quality, yet lowest-cost solution on the market for speaker-attributed transcripts. We're... proud to partner with the Notion team.show more

🖤

We 💚 our friends @baseten! Proud to partner with you to ensure all of our customers have the most powerful AI Meeting Notes!

@zachtratar is so handsome

@NotionHQ Congrats but I couldn’t find more than 10-15 models on your platform, which model you use for this voice transcription and how can I find other models

Love the Notion ↔ Baseten loop — product in the wild, infra learning from real usage. Same pattern we’re seeing with agent swarms: the model layer gets sharp fast; the missing piece is proving what the agent did after the session ends. Curious if Meeting Notes traces ever need a portable receipt outside Notion (compliance / multi-agent handoff).

Does the speaker attribution survive into the Notion page as navigable structure, or does it flatten once the transcript lands? We built DeepRead around the same question: Kindle highlights nested in the book's chapter structure, not flattened into a list. A book stays a shape you can move through, not an export you file away.

Amazing collaboration, can't wait to see how both platforms continue to innovate together!

Sounds like a powerhouse collaboration—excited to see where this innovation takes us!

exciting

collaborating like this shows how powerful integrations can really be

Teams using each other's products end-to-end is a good smell. Voice quality at low cost is the meeting-notes race that actually matters.

Using each other's product as infrastructure is a better partnership story than a logo slide. Speaker-attributed transcripts at that cost curve is the real flex.