What should a solutions architect do to meet these requirements?
Process the audio files by using Amazon Kinesis Video Streams. Use an AWS Lambda function to scan for known PII patterns.
When an audio file is uploaded to the S3 bucket, invoke an AWS Lambda function to start an Amazon Textract task to analyze the call recordings.
Configure an Amazon Transcribe transcription job with PII redaction turned on. When an audio file is uploaded to the S3 bucket, invoke an AWS Lambda function to start the transcription job. Store the output in a separate S3 bucket.
Create an Amazon Connect contact flow that ingests the audio files with transcription turned on. Embed an AWS Lambda function to scan for known PII patterns. Use Amazon EventBridge to start the contact flow when an audio file is uploaded to the S3 bucket.
Explanations:
Amazon Kinesis Video Streams is designed for video data, not audio transcription. This option also doesn’t inherently provide a means to capture the text from audio files, nor does it focus on the transcription and PII redaction requirement.
Amazon Textract is primarily used for extracting text from images and documents, not audio files. This option does not address the transcription of audio, which is necessary to convert speech to text.
Amazon Transcribe can transcribe audio files and has built-in PII redaction capabilities. By invoking a Lambda function upon the upload of an audio file to S3, it efficiently processes the audio and stores the redacted text output in a separate S3 bucket, meeting the requirements.
Amazon Connect is a contact center service and not directly applicable for processing audio files stored in S3 for transcription. While it can transcribe calls, it does not align with the requirement to trigger from S3 uploads. Additionally, it does not provide a straightforward mechanism for PII scanning within the context described.