Overview - Media Analysis Solution


Amazon Web Services (AWS) offers powerful and cost-effective services to help customers process, analyze, and extract meaningful data from their audio, image, and video files. Customers who want to obtain a broader understanding of their media libraries can use these services to develop solutions to analyze and extract valuable metadata from their media files. Customers can also use various machine learning tools and algorithms to develop their own analytics solutions in the AWS Cloud. However, developing these solutions can require extensive knowledge of deep-learning algorithms and artificial intelligence (AI) services.

To help customers more easily analyze and understand their media files, AWS offers the Media Analysis Solution, a reference implementation that uses serverless, AWS-native AI services to automatically extract valuable metadata from media files. This solution combines Amazon Rekognition, which provides highly accurate object, scene, and activity detection; facial analysis and recognition; pathing; and celebrity detection in videos and images, Amazon Transcribe, an automatic speech recognition service, and Amazon Comprehend, to automatically transcribe audio and extract key phrases and entities from transcripts, to quickly and seamlessly extract key details from their media files in their AWS accounts without machine learning expertise.


You are responsible for the cost of the AWS services used while running the Media Analysis Solution. The total cost for running this solution depends on the size of media and metadata files stored in Amazon Simple Storage Service (Amazon S3), the duration and number of executed AWS Lambda functions, the number of AWS Step Functions state transitions, running the solution’s Amazon Elasticsearch Service cluster, and the size and length of media files analyzed with Amazon Rekognition, Amazon Transcribe, and Amazon Comprehend. You will also incur charges for requests made to the Amazon API Gateway. For full details, see the pricing webpage for each AWS service you will be using in this solution.