# TwelveLabs Marengo Embed 3.0 reaches general availability in Amazon Bedrock Knowledge Bases

_Thursday, September 10, 2026 at 5:15 PM EDT · AI · Latest · Tier 2 — Notable_

![TwelveLabs Marengo Embed 3.0 reaches general availability in Amazon Bedrock Knowledge Bases — Primary](https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/10/ML-21835-featured-image.png)

Amazon Web Services said TwelveLabs Marengo Embed 3.0 is now generally available as an embedding model in Amazon Bedrock Knowledge Bases.

The model jointly encodes video, audio, images and text into a 512-dimensional vector space, letting managed knowledge bases generate multimodal embeddings without a custom pipeline of transcription, frame extraction and synchronization. AWS said ingestion handles segmentation, frame sampling and transcription internally, and that the Retrieve API can serve downstream applications.

The company listed availability in US East (N. Virginia) and US West (N. California), with embedding generation charged at standard Bedrock model invocation rates.

## Sources

- [AWS Machine Learning Blog](https://aws.amazon.com/blogs/machine-learning/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0/)

---
Canonical: https://techandbusiness.org/newswire/PQMedu0fHf8ZYwFWN-6Ruv
Retrieved: 2026-09-11T04:24:51.626Z
Publisher: Tech & Business (techandbusiness.org)