1
Choose the suitable book, article, newsletter etc. content to be translated from text-to-speech.
2
A Lambda function retrieves the text and sends it to Amazon Polly for synthesis.
3
Choose the required language and a voice model. Amazon Polly converts the text-to-speech and stores the audio file in S3 bucket.
4
The S3 bucket consists of the final text-to-speech audio which can be downloaded.