Overview
Content Localization on AWS helps to extend the reach of your video-on-demand content by creating multi-language subtitles, powered by artificial intelligence (AI). Producing accurate, multi-language subtitles for videos is both complex and labor-intensive, with many personnel hours spent transcribing, subtitling, translating, and reviewing media assets. With this AWS Solution, you can automate those manual processes and still control the result. It includes a simple UI where you can upload, analyze, and extract valuable metadata from video files using native AWS AI services.
Benefits
Upload and analyze videos, and work with automatically generated video subtitles using a simple web-based user interface.
You can review subtitles and make corrections within the application. Once you are satisfied with the subtitles, rerun the workflow using the corrected input to regenerate downstream results.
Generate custom vocabularies and terminologies using the corrections you make to the subtitles. Provide these customizations when you upload a video and configure the automated workflow.
Technical details
You can automatically deploy this architecture using the implementation guide and the accompanying AWS CloudFormation template.
Step 1
The AWS CloudFormation template deploys an instance of the Media Insights on AWS.
Step 2
An Amazon CloudFront distribution to serve the solution’s web application.
Step 3
An Amazon Simple Storage Service (Amazon S3) web source bucket for hosting the static web application.
Step 4
An Amazon Cognito user pool to provide a user directory.
Step 5
Cognito identity pool to provide federation with AWS Identity and Access Management (IAM) for authentication and authorization to the web application.
Step 6
Amazon API Gateway endpoints for the Media Insights on AWS workflow API, the Media Insights on AWS data plane API and the Amazon OpenSearch Service API endpoint.
Step 7
An AWS Step Functions workflow created by Media Insights on AWS. The content localization workflow consists of AWS Lambda functions that run jobs in Amazon Transcribe, Amazon Translate, AWS Elemental MediaConvert, and Amazon Polly.
These Lambda functions also interact with the Media Insights on AWS data plane API to store and retrieve media objects and metadata returned by media analysis jobs. The workflow can also optionally run Amazon Rekognition and Amazon Comprehend to provide additional analysis of the input.
Step 8
A Lambda function to extract, transform, and load media metadata from the Media Insights on AWS data pipeline into an OpenSearch Service cluster. This Lambda function is invoked by the Media Insights on AWS data plane Amazon DynamoDB stream whenever asset metadata is modified in the Media Insights on AWS data plane.
Step 9
An OpenSearch Service cluster to index media metadata.
Step 1
The AWS CloudFormation template deploys an instance of the Media Insights on AWS solution.
Step 2
An Amazon CloudFront distribution to serve the solution’s web application.
Step 3
An Amazon Simple Storage Service (Amazon S3) web source bucket for hosting the static web application.
Step 4
An Amazon Cognito user pool to provide a user directory.
Step 5
Cognito identity pool to provide federation with AWS Identity and Access Management (IAM) for authentication and authorization to the web application.
Step 6
Amazon API Gateway endpoints for the Media Insights on AWS workflow API, the Media Insights on AWS data plane API and the Amazon OpenSearch Service API endpoint.
Step 7
An AWS Step Functions workflow created by Media Insights on AWS. The content localization workflow consists of AWS Lambda functions that run jobs in Amazon Transcribe, Amazon Translate, AWS Elemental MediaConvert, and Amazon Polly.
These Lambda functions also interact with the Media Insights on AWS data plane API to store and retrieve media objects and metadata returned by media analysis jobs. The workflow can also optionally run Amazon Rekognition and Amazon Comprehend to provide additional analysis of the input.
Step 8
A Lambda function to extract, transform, and load media metadata from the Media Insights on AWS data pipeline into an OpenSearch Service cluster. This Lambda function is invoked by the Media Insights on AWS data plane Amazon DynamoDB stream whenever asset metadata is modified in the Media Insights on AWS data plane.
Step 9
An OpenSearch Service cluster to index media metadata.
- Publish Date
Related content
Media Insights on AWS is a framework that makes it easier for developers to build serverless applications that process video, images, audio, and text with AI and multimedia services on AWS. This solution is a development framework for applying machine learning services to media workflows.