Home icon

Summarize call transcriptions securely with Amazon Transcribe and Amazon Bedrock Guardrails

Machine Learning Blog



This article discusses how to securely summarize call transcriptions using Amazon Transcribe for speech-to-text and Amazon Bedrock for summarization and personal identifiable information (PII) redaction.

Specifically, the article covers:

  • Overview of the solution architecture using AWS services like Step Functions, Lambda, SNS, and S3
  • Steps to deploy the solution using CloudFormation template and required prerequisites
  • How to invoke Amazon Bedrock's generative AI model (Anthropic's Claude 3 Haiku) with instructions and transcript
  • Using Amazon Bedrock Guardrails to redact sensitive PII from the generated summaries
  • Potential ways to expand and customize the solution for different use cases
  • Instructions to clean up the deployed resources


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

Nov 6
2024
Unearth insights from audio transcripts generated by Amazon Transcribe using Amazon Bedrock
Aug 21
2024
Enhance call center efficiency using batch inference for transcript summarization with Amazon Bedrock
Apr 30
2024
Enhance customer service efficiency with AI-powered summarization using Amazon Transcribe Call Analytics
Mar 25
2024
Best practices for building secure applications with Amazon Transcribe

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.