Video-first foundation models for deep video understanding.
Description
Twelve Labs creates advanced video-first foundation models that integrate visual, audio, and speech information. Their technology enables deep video understanding and intelligent retrieval for developers and enterprises.
Industry
Technology
Page type
Captured
March 23, 2026
Theme
Fonts
Milling Duplex 1mm, Milling Triplex 1
Technologies
Framer Motion, Framer Sites, Google Analytics, Google Tag Manager, Osano