TwelveLabs’ Marengo Embed 3.0 for advanced video understanding now in Amazon Bedrock
News
TwelveLabs has launched Marengo Embed 3.0 on Amazon Bedrock, offering advanced video understanding and multimodal embedding capabilities.
- Enhanced video processing capacity up to 4 hours and 6GB files
- Improved sports analysis with better gameplay and player movement understanding
- Expanded language support from 12 to 36 languages
- Enables multimodal search by combining images and text in embedding requests
- Available in US East, Europe, and Asia Pacific regions
- Supports both synchronous and asynchronous inference
The model allows developers to build sophisticated video search, recommendation systems, and content analysis applications with industry-leading performance.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Dec 16
2025
2025
Unlocking video understanding with TwelveLabs Marengo on Amazon Bedrock
Sep 9
2025
2025
TwelveLabs’ Marengo Embed 2.7 can now be used for synchronous inference in Amazon Bedrock
Sep 11
2026
2026
Amazon Bedrock Managed Knowledge Base now supports multimodal embeddings for video, audio, and image content with TwelveLabs Marengo 3.0
Jul 15
2025
2025
TwelveLabs video understanding models are now available in Amazon Bedrock
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.