VP Land sits down with Soyoung Lee from Twelve Labs, a company building multimodal video foundation models that can understand everything inside a video. Their AI technology is set to revolutionize the way creators and businesses search, analyze, and manage their video content.
⏱ CHAPTERS
00:00 Intro
00:20 What is Twelve Labs?
01:07 Building video-first AI models
02:36 Twelve Labs' unique approach
03:49 Applications of Twelve Labs' technology
06:00 A single, powerful model
06:57 Image and audio-based video search
08:08 AI in the media landscape
📰 CREDITS
Producer & Host: Joey Daoud
Production Manager: Steve Regalado
Director of Photography: Justin Guo
Editors: Kirill Slepynin & Jan Gonzales
Graphic Designer: Kristina Leongard
Generation Examples
Comparison against existing models
Related articles
We are excited to announce Marengo 2.7 - a breakthrough in video understanding powered by our innovative multi-vector embedding architecture!
.png)
Introducing our new Embed API in Open Beta, enabling customers to generate state-of-the-art multimodal embeddings.
We had fun interacting with the AI community in Denver!
Twelve Labs co-hosted our first in-person hackathon in Los Angeles!
