With Amazon Polly, you only pay for what you use. There is no setup cost and no minimum fee.
With Amazon Polly, you are charged based on the number of characters of text that you convert either to speech or to Speech Marks metadata. You can cache and replay Amazon Polly’s generated speech at no additional cost. You can also cache and reuse Amazon Polly’s generated Speech Marks at no additional cost.
The Amazon Polly free tier includes 5 million characters per month for speech or Speech Marks requests, for the first 12 months, starting from the first request for speech.
Pay-as-you-go $4.00 per 1 million characters for speech requests (when outside the free tier). Pay-as-you-go $4.00 per 1 million characters for Speech Marks requests (when outside the free tier).
|Example||Text Length||Speech Duration||Cost|
|1,000 requests, 1,000 characters per request||1 million characters||~23 hours, 8 min
|10,000 requests, 100 characters per request
||1 million characters||~23 hours, 8 min||$4.00|
|2016 Amazon Shareholders Letter||1.3k characters, single page||~1 min. 40 sec
|Average email message
||~3.1k characters||~4 min||$0.02|
|Typical news article
||~6.5k characters, three pages||~9 min
|"A Christmas Carol" by Charles Dickens||~165k characters, 64 pages||~3 hours 50 min||$0.66|
|"Adventures of Huckelberry Finn" by Mark Twain
||~600k characters, 224 pages||~13 hours 50 min
- Average length of a single narration text: 100 characters
- Number of narration texts per animated production: 25
|2.5k characters per animation||~3.5 min||$0.01|
- Average spoken response length: 100 characters
- Requests per user per month: 300
|30k characters per user per month||~42 min||$0.12
- Average length of single phrase from avatar: 100 characters
- Number of phrases produced by avatar: 25
- Need for Speech Marks to synchronize lips
2.5k characters of synthesized speech
2.5k characters of Speech Marks data
|Storytelling with highlightext text for children:
- Length of text for the story: 10k characters
- Need for Speech Marks to synchronize highlighted text
10k characters of synthesized speech
10k characters of Speech Marks data