# Condé Nast cuts video search time from 250 minutes to 2 minutes using Amazon Bedrock and TwelveLabs Marengo

Digest AI · Enterprise & Industry · published 2026-09-29T15:55:17Z

Canonical: https://digestai.news/story/conde-nast-cuts-video-search-time-from-250-minutes-to-2-minutes-using

## Summary

Condé Nast’s editorial teams spent an average of **250 minutes per task** manually searching through **140,000+ videos** using only titles and descriptions. This slowed content discovery for brands like *Vogue*, *GQ*, and *Wired*, hurting revenue capture in a fast-moving media environment. The bottleneck stemmed from traditional search tools’ inability to analyze video content beyond metadata.

The publisher partnered with **AWS’s Generative AI Innovation Center** to build a **multimodal video discovery system** using **Amazon Bedrock** and the **TwelveLabs Marengo embedding model**. The solution processes video transcripts, visuals, and audio into vector embeddings, enabling intent-based semantic search. By decoupling embedding generation from search serving, the team scaled the system efficiently. Results include a **99.2% reduction in discovery time** (from 250 minutes to **under 2 minutes**), a **90% drop in manual review effort**, and **$800,000 in annual savings**. The architecture’s high availability and modular design also ensure reliability for daily use.

## Key points

- Condé Nast’s video search time dropped from 250 minutes to under 2 minutes per task using TwelveLabs Marengo embeddings on Amazon Bedrock
- System combines video transcripts, audio, and visuals into vector embeddings for intent-based semantic search, reducing manual review by 90%
- Estimated annual savings of $800,000 from productivity gains across 140,000+ videos, with multi-AZ design ensuring uptime

## Why it matters

This case study demonstrates how multimodal AI can transform media workflows by replacing slow, manual video searches with semantic understanding. The decoupled architecture and cost savings offer a blueprint for industries managing large video archives, from broadcasters to enterprise media teams.

## Sources

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 Machine Learning Blog, 2026-09-29, primary source)

## Cite

Digest AI, "Condé Nast cuts video search time from 250 minutes to 2 minutes using Amazon Bedrock and TwelveLabs Marengo", 29 September 2026, https://digestai.news/story/conde-nast-cuts-video-search-time-from-250-minutes-to-2-minutes-using

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. 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
JSON: https://digestai.news/story/conde-nast-cuts-video-search-time-from-250-minutes-to-2-minutes-using.json