TwelveLabs Marengo 3.0

TwelveLabs Marengo 3.0 is an advanced multimodal embedding model that achieves human-like video understanding by fusing video, audio, and text data. It enables precise video search and retrieval at scale, tracking objects, movement, and emotions through time. The model is available through TwelveLabs and Amazon Bedrock for developers and enterprises to integrate into AI applications.