{"version":1,"type":"story","url":"https://digestai.news/story/amazon-bedrock-adds-marengo-3-0-for-video-image-and-audio-search","json":"https://digestai.news/story/amazon-bedrock-adds-marengo-3-0-for-video-image-and-audio-search.json","markdown":"https://digestai.news/story/amazon-bedrock-adds-marengo-3-0-for-video-image-and-audio-search.md","slug":"amazon-bedrock-adds-marengo-3-0-for-video-image-and-audio-search","headline":"Amazon Bedrock Adds Marengo 3.0 for Video, Image, and Audio Search","summary":"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.\n\nThe 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.\n\nWith 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.","keyPoints":["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"],"whyItMatters":"By simplifying multimodal search, Bedrock lowers the barrier for industries that rely on large media archives, improving productivity and unlocking new use cases in sports, security, and education.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Amazon","TwelveLabs"],"models":["Marengo Embed 3.0"],"people":[]},"firstPublishedAt":"2026-09-10T21:15:39Z","updatedAt":"2026-09-10T21:15:39Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0","url":"https://aws.amazon.com/blogs/machine-learning/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0","publishedAt":"2026-09-10T21:15:39Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Amazon Bedrock Adds Marengo 3.0 for Video, Image, and Audio Search\", 10 September 2026, https://digestai.news/story/amazon-bedrock-adds-marengo-3-0-for-video-image-and-audio-search","publisher":"Digest AI","title":"Amazon Bedrock Adds Marengo 3.0 for Video, Image, and Audio Search","datePublished":"2026-09-10T21:15:39Z","url":"https://digestai.news/story/amazon-bedrock-adds-marengo-3-0-for-video-image-and-audio-search"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}