Automated Audio Transcription from AWS S3

This n8n workflow automates the process of transcribing audio files stored in an AWS S3 bucket. It begins with a manual trigger, allowing the user to initiate the process when needed. The workflow fetches all files from a specified S3 bucket, then sequentially processes each file through AWS Transcribe to generate a text transcription. The transcription job’s name is dynamically generated based on the filename, replacing spaces with hyphens for compatibility. This setup is highly practical for automating the conversion of audio content into editable text, useful in scenarios like podcast transcription, voice note processing, or archiving audio data with searchable transcripts.