Amazon Polly is an AWS cloud service that turns written text into natural-sounding speech for apps such as contact centres, AI voice agents and e-learning.
In plain words
You send Polly text and it returns spoken audio in a chosen voice, and you pay only for the text it converts. Its generative engine is its largest speech model. In October 2026 AWS upgraded that engine for more expressive speech and better reading of numbers, prices and addresses, reaching 57 voices in 11 languages, with Hindi and Finnish new. Existing apps get it without code changes, and a streaming API takes text in while sending audio back, for live uses such as voice agents.
A quick example
AWS's samples include a voice called Kenneth reading back an order confirmation: the tracking number, the delivery date and time, the total price and the street address.
Where you'll meet it
- Contact centres and phone systems.
- AI voice agents and characters in games.
- E-learning, media and accessibility tools.
Related
Sources
- DocsWhat is Amazon Polly?, AWS docs · read 22 Oct 2026
- DocsAmazon Polly delivers a major upgrade to its Generative engine, AWS Machine Learning Blog · read 22 Oct 2026
- DocsGenerative voices, AWS docs · read 22 Oct 2026
Checked by WhatIsAI against the sources above · 22 Oct 2026. Spotted an error? Report it.