TwelveLabs’ Innovative Video Understanding Models Now Available in Amazon Bedrock

AWS is announcing that TwelveLabs video understanding models are now available in Amazon Bedrock, providing the ability to search through videos for specific details, as well as classify scenes, summarize, and extract insights. Centering precision and reliability, TwelveLabs’ AI models introduce innovative natural language-driven video analysis to Amazon Bedrock.

TwelveLabs’ Marengo, the company’s breakthrough video foundation model, analyzes frames and their temporal relationships alongside speed and sound, drastically altering video search and classification. Another of TwelveLabs’ models, Pegasus, is a video-first language model that integrates visual, audio, and speech information to enable deep video understanding for text generation.

To help make videos as searchable as text, these models were trained on Amazon SageMaker HyperPod, delivering precise test summaries, metadata operation, and creative optimization.

With TwelveLabs’ models now available via Amazon Bedrock, enterprises can utilize natural language to search video content, including queries such as “show me the first touchdown of the game” or “find the scene where the main characters first meet,” highlighting that exact moment. Additionally, these models can be used to develop applications that inherently understand video content, generating text such as titles, topics, hashtags, summaries, chapters, or highlights.

“For example, you can find recurring themes in customer feedback or spot product usage patterns that weren’t obvious before,” explained Channy Yun, principal developer advocate, AWS Cloud, AWS. “Whether you have hundreds or thousands of hours of video content, you can now transform that entire library into a searchable knowledge resource while maintaining enterprise-grade security and performance.”

To learn more, please visit https://aws.amazon.com/?nc2=h_home.