Amazon Bedrock Now Handles Video, Audio, and Images Like a Pro with TwelveLabs Marengo 3.0

AWS just dropped TwelveLabs Marengo 3.0 in Amazon Bedrock Managed Knowledge Base, letting you search through video, audio, and image content using natural language—no transcription needed. The model captures visual scenes and speech directly as multimodal embeddings, so you can jump straight to the exact moment in a video that matches your query, perfect for sports analytics, media, security, and education use cases.