Amazon Polly

What Amazon Polly is

Amazon Polly converts text into speech through a web interface and API. It lists 42 languages, voice cloning, and a maximum input of 6,000. Voice choices are organized as Standard, Neural, Long-Form, and Generative, with audio exports in MP3, OGG Vorbis, OGG Opus, PCM, mu-law, and a-law. Pricing is based on processed characters and billed monthly. Standard costs $4 a month for Standard voices and Speech or Speech Marks requests; Neural is $16 a month for Neural voices and those request types. Long-Form costs $100 a month for Long-Form voices and those request types, while Generative costs $30 a month for Generative voices and Speech requests. Its free tier lists 5 million Standard characters, 1 million Neural characters for 12 months, 500,000 Long-Form characters for 12 months, and 100,000 Generative characters for 12 months. Amazon Polly is listed as founded in 2006 and headquartered in Seattle, Washington, United States.

Who it suits

Amazon Polly suits developers or teams seeking text-to-speech through an API or web interface, with multiple voice categories and audio export choices. Its listed language coverage and free-tier character allowances may help those evaluating different volumes or voice types.

Limits

The free tier includes 5 million Standard characters and, for 12 months, 1 million Neural, 500,000 Long-Form, and 100,000 Generative characters. Paid plans are billed monthly for processed characters and cover the voice category and request types listed for each plan.

Getting started

1. Visit the Amazon Polly website.
2. Use the web interface or API to access Polly.
3. Start with the free tier or select a paid voice plan.
4. Choose the voice category that matches your requests: Standard, Neural, Long-Form, or Generative.
5. Export audio in one of the listed formats.

Verdict

Amazon Polly offers several voice categories, access methods, and export formats, with a free tier alongside monthly paid plans. Buyers should compare the included request types and character allowances for the voice category they need.