Twelve Labs is a pioneering company focused on developing multimodal artificial intelligence that enables machines to analyze and understand video content in a way that mimics human perception. Founded in 2020, Twelve Labs aims to bridge the gap between traditional AI systems and human-like video comprehension by leveraging cutting-edge technology to create models that learn rich, multimodal representations from video data. This innovative approach not only enhances video search capabilities but also allows for more meaningful interactions with video content across various applications.
Our flagship products include advanced video APIs, which help developers integrate sophisticated video understanding into their applications. The state-of-the-art Marengo model allows for precise scene search, while Pegasus, our video-language model, empowers users to generate textual descriptions and perform complex queries about video content. We believe this technology can redefine how users interact with video, making it easier for them to sift through and derive insights from large amounts of information. Our team, composed of experts in AI and machine learning, is dedicated to pushing the boundaries of what is possible with video understanding, transforming industries ranging from entertainment to security and education.