Amazon Polly Getting Started
AWS Skill Builder
Last updated June 26, 2025
Amazon Polly Getting Started is a free, one-hour introduction to Amazon Polly, AWS's managed service for turning written text into natural-sounding speech. The idea is straightforward: give it text and it returns spoken audio in a lifelike voice, so an application can read content aloud rather than only display it. This is a short orientation to the service — it covers what Polly is for, the kinds of problems it solves, its benefits and typical use cases, the technical concepts behind it, how it relates to other parts of the AWS Cloud, and how its pricing works, before a closing section on how to use it. It is the lightest of AWS's service introductions, pitched as a first look rather than a deep build.
What you'll learn
- What Polly is and the problems it solves
- Benefits and typical use cases for TTS
- The technical concepts behind it
- How Polly relates to other AWS Cloud components
- How its pricing is structured
- How to use Amazon Polly
Frequently asked questions about Amazon Polly Getting Started
Who is Amazon Polly Getting Started for?
Beginners — including developers, architects, and project leads — who want a quick, plain orientation to converting text into natural-sounding speech with a managed service, using Amazon Polly.
Is Amazon Polly Getting Started free?
Yes — Amazon Polly Getting Started is completely free to take.
What are the prerequisites for Amazon Polly Getting Started?
A basic understanding of the AWS Cloud.
Why we suggest this course
A quick, no-cost orientation to text-to-speech: what a managed speech service does, where it fits, and how it is priced, for someone deciding whether it suits their application. One thing to know: this is an introduction to a single AWS service, so it is vendor-specific by design rather than a general tour of speech synthesis — and it is a brief overview, weighted toward the service's purpose, use cases, and pricing more than hands-on practice. What you learn applies to Amazon Polly in particular, though the underlying idea of converting text to speech is common across tools.