Speech Synthesis Using Amazon Polly

Amazon Polly is a text-to-speech speech service that allows you to convert your text into a lifelike speech. You can add Speech Synthesize Markup Language (SSML) tags to your text to manipulate the speech accordingly. You can integrate Amazon Polly into your applications, like book readers and news applications, use a special SSML tag to introduce the news speaking style, and even add whispering and breathing effects that make the speech more natural.

In this Cloud Lab, you’ll learn to generate speech using the Polly through the AWS Console. You’ll also see some interesting SSML tags, functionalities, and usage and use the Amazon Comprehend service to detect Personally Identifiable Information (PII) entities in the text and then use the SSML tags to whisper these entities. You’ll get hands-on experience with the application that uses Amazon Polly and Comprehend.

After completing this Cloud Lab, you’ll be capable enough to explore Amazon Polly further and create interesting text-to-speech applications. Below is the architecture diagram of this Cloud Lab: