Amazon Bedrock Adds Marengo 3.0 for Video, Image, and Audio Search
Amazon announced the general availability of TwelveLabs Marengo Embed 3.0 as an embedding model in its Bedrock Knowledge Bases, enabling natural‑language search across video, audio, and image assets.
Key points
- Marengo Embed 3.0 is a 512‑dim multimodal embedding model now available in Bedrock Knowledge Bases
- Bedrock handles segmentation, transcription, and vector indexing automatically, enabling semantic search over video, audio, and images
- The release supports S3, SharePoint, Confluence, and is priced per Bedrock model invocation
The new multimodal model encodes media and text into a 512‑dimensional vector space, allowing Bedrock to automatically segment, transcribe, and embed content from S3, SharePoint, or Confluence. A demo using a 10‑minute FIFA World Cup clip shows how users can query moments like “penalty kick in the second half” and receive time‑stamped results.
With Bedrock’s fully managed Retrieval Augmented Generation service, teams in sports analytics, media, security, education, and retail can unlock semantic search without building custom pipelines. The feature is available in us‑east‑1 and us‑west‑1, and pricing follows Bedrock’s standard model invocation rates.
Model page: Marengo Embed 3.0 →
Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0
AWS Machine Learning Blog · 10 September 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Eric Kim. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Introducing Mistral Large 4 · 7 src
- OpenAI boosts GPT-6 speed by 50% in 28 Days update · 1 src
- Reflection AI debuts Beam, a 501B open-weight model rivaling GLM 5.2 with 3-4x less compute · 10 src
- Author tests four AI assistants on flawed forecasting scenarios · 1 src
- Anthropic prompts users to share voice data to enhance AI models · 8 src
Comments
via GitHub Discussions