Amazon Bedrock Data Automation now supports extraction of custom insights from audio

Amazon Bedrock Data Automation (BDA) now supports extraction of custom GenAI-powered insights from audio by specifying the desired output configuration through blueprints. BDA is a GenAI-powered capability of Bedrock that streamlines the development of generative AI applications and automates workflows involving documents, images, audio, and videos. Developers can now extract custom insights from audio using blueprints, which contain their desired output including a list of field names, the data format in which the response for the field is to be extracted as well as natural language instructions for each field. Developers can get started with blueprints by either using a catalog blueprint or creating a blueprint tailored to their needs.

With this launch, developers can extract custom insights such as summaries, key topics, intents, and sentiment from a variety of voice conversations such as customer calls, clinical discussions, and meetings. Insights from BDA can be used to improve employee productivity, reduce compliance costs, and enhance customer experience, among others. For example, customers can improve productivity of sales agents by extracting insights such as summaries, key action items, and next steps from conversations between sales agents and customers.

Amazon Bedrock Data Automation is available in US West (Oregon) and US East (N. Virginia) AWS Regions.

To learn more, visit the Bedrock Data Automation page, Amazon Bedrock Pricing page, or view documentation.