Home icon

Make videos accessible with automated audio descriptions using Amazon Nova

Machine Learning Blog



This article describes an innovative approach to making videos accessible for visually impaired people using AWS AI services, specifically Amazon Nova, Rekognition, and Polly.

  • Over 2.2 billion people globally have vision impairment
  • Current audio description services cost around $25 per minute
  • Amazon Nova offers three multimodal foundation models for automated video description
  • The solution involves:
  • Using Amazon Rekognition to segment video scenes
  • Using Amazon Nova Pro to analyze video content
  • Converting scene descriptions to audio with Amazon Polly

The workflow automates audio description creation, significantly reducing time and cost while improving accessibility for visually impaired audiences. The solution can be applied to various types of visual media beyond movies and TV shows.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Apr 17
2026
Power video semantic search with Amazon Nova Multimodal Embeddings
Oct 28
2025
Announcing Amazon Nova Multimodal Embeddings
Feb 5
2026
A practical guide to Amazon Nova Multimodal Embeddings
Apr 8
2026
Building intelligent audio search with Amazon Nova Embeddings: A deep dive into semantic audio understanding

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.