Analytics & AI

Amazon Polly

Timenot billed
Bytesnot billed
Callsbilled

In one line

You pay per character of text synthesized. Generative and long-form voices cost far more than standard.

What gets missed

Speech Marks requests bill at the same per-character rate as audio, so asking for both doubles the text you pay for. Replaying a stored MP3 costs nothing; re-synthesizing the same string charges again.

Find it on your bill

Filter Cost Explorer or your Cost and Usage Report by these usage types. A usage type with no region prefix means us-east-1.

SynthesizeSpeech-Characters
SynthesizeSpeechNeural-Characters
SynthesizeSpeechGenerative-Characters

Bills the same way

These services turn exactly the same meters, so what you learn here transfers.