Skip to content

Amazon Polly

#203 · Level 3 · Modern architecture · AI and machine learning

Amazon Polly turns text into a natural-sounding voice (text to speech). You can choose from many languages and many voices (male, female). With special marks called SSML, you can control pronunciation, pauses and speed. The created audio can be saved as a file, or played in an app right away. It does the opposite of Amazon Transcribe.

A reader who reads any text aloud to you.

Recording everything with people is costly; visually impaired people need text read aloud.

Reading articles aloud, phone announcements, learning apps.

Azure AI Speech (text to speech)

For details and the latest information, see the official documentation: