# Condé Nast cuts video search time from 250 minutes to 2 minutes

> Using Amazon Bedrock and OpenSearch, the publisher reduced discovery time by 99% and expects $800 K in yearly savings.

Oossa · 2026-09-29 · https://oossa.com/en/conde-nast-cuts-video-search-time-from-250-minutes-to-2-minutes

Condé Nast’s editors now find clips in under two minutes instead of 250 minutes. The change comes from an AI‑driven search tool built with Amazon Bedrock, Amazon OpenSearch Service and TwelveLabs’ Marengo embedding model. The system looks inside video transcripts, visuals and audio to match natural‑language queries. It is already used across Vogue, GQ, Vanity Fair and Wired.

## The facts

- 140,000+ videos processed
- 99.2% reduction in discovery time (250 min → ~2 min)

## Why it matters

Faster video search lets editors respond quickly to advertisers and repurpose hidden content, saving time and about $800 K each year.

## Sources & references

1. [How Condé Nast built multimodal video discovery with Amazon Bedrock](https://aws.amazon.com/blogs/machine-learning/how-conde-nast-built-multimodal-video-discovery-with-amazon-bedrock/) – AWS, 2026-09-29

Last updated: 2026-09-29