Soyoung Lee, TwelveLabs | AWS Summit NYC 2025
summary
Company claims a multimodal video understanding stack that ingests video, audio and text to create searchable embeddings and run video-language tasks at scale. It ships an embedding model Marengo and a video-language model Pegasus, exposes APIs and a turnkey search engine, and supports major vector stores including S3 Vector Store. Deployments index videos into embeddings, add a search API (demoed in ~20 minutes), and serve media, sports, ad tech and safety customers across petabyte libraries with 50,000 developer users and ~110 staff.
AI-written summary · about
