Transcribe, Translate, Polly to convert audio to a different user-specific language by coordinating AI Services & Orchestrating them with Step Functions

Architecture

  1. Upload audio file to S3 Bucket
  2. Trigger AI Pipeline
  3. Convert Audio file to audio-specific language text
  4. Wait for Transcription Job Completion
  5. Parallel State Step Functions for convert audio-specific language text to use specific language in text
  6. Parallel State Step Functions for Identifying the sentiment of the audio
  7. Convert user-specific language text to user-specific audio file
  8. Lambda’s Orchestration by using Step Functions
  9. IAM Roles used for Lambda’s & Step Functions
  10. Output audio file in a user-specific language

Detailed Architecture Flow

  1. Upload an audio file to S3 Bucket → User or an application uploads an audio file to an input S3 bucket
start-ai-pipeline
start-transcribe-lambda
transcribe-status-lambda
translate-lambda
comprehend-sentiment-lambda
start-polly-lambda
Amazon States Language for Step Functions Orchestration

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Sasi Akki

Sasi Akki

3 Followers

Helping fellow engineers learn about the cloud, Pre-Sales Solution Architect at NCS. AWS Community Builder