How was this content?
- Learn
- Seeing is understanding – TwelveLabs unlocks the full potential of video for the world
Seeing is understanding – TwelveLabs unlocks the full potential of video for the world
TwelveLabs has two primary models: Marengo and Pegasus. Marengo is a multimodal embedding model that captures the visual, audio, and spatial-temporal context of videos to power any-to-any video search. This capability allows users to easily search and retrieve video data from massive archives. Pegasus is a video language model that analyzes video content to generate text-based outputs like summaries and analyses to structured outputs like metadata and JSON to power downstream video workflows and tools. It is designed to address the practical challenges of real-world video understanding and analysis, from fine-grained temporal reasoning to handling content that spans from seconds to hours. It has been adopted by a broad spectrum of users: from enterprises managing video datasets comprised of millions of hours to individuals pursuing creative projects. With these models, TwelveLabs helps users effectively search, classify, and utilize video data for various applications. “Nearly 90% of the world’s data is unstructured, a majority of it in video, yet most of it is unsearchable. We are now able to address this challenge, surfacing highly contextual videos to bring experiences to life, similar to how humans see, hear, and understand the world around us,” said Jae Lee, CEO and co-founder of TwelveLabs. From media giants like MLSE and Washington Post to enterprises in advertising, manufacturing, and government, TwelveLabs powers video intelligence across industries where visual data drives decisions. The company also partners with leading media asset management providers including Mimir, Iconik, and Adobe.
Find out how TwelveLabs scaled video AI from research to global production. Read the full case study.

Over 330,000 have joined AWS Activate since its inception in 2013, accessing a range of resources to help build, grow, and scale their startup. This includes unlocking AWS Activate Credits, which can be used to help cover the costs of AWS services and solutions, from compute, database, and storage; to machine learning, containers, applications, and more. AWS Activate has already provided more than $7 billion in credits to startups, and yours could be next to benefit. Find out more about AWS Activate today.
How was this content?