The plugin itself was jointly designed by Amazon’s AWS team and managed WordPress platform provider WP Engine, and takes advantage of Amazon’s text-to-speech service, Polly.
First introduced at Amazon’s re:Invent developer event back in November 2016, Polly uses machine learning technologies under the hood to deliver more life-like speech. For example, Polly understands that the word “live” would be pronounced differently based on its usage. In the phrases “I live in Seattle” and “Live from New York,” the word is spelled the same but is not spoken in the same way. That means the voices sound more natural than some other, more basic voice-to-text engines.
The Polly speech engine launched with 47 male and female voice and support for 24 languages. Since then, Amazon added support for Korean, another 5 languages, and made Polly available in all regions in the AWS partition.
The technology’s capabilities have also evolved, with added support for things like whispering, speech marks, a timbre effect, and dynamic range compression. These sorts of voice technology advancements are also things that make Alexa sound more natural, too. Similar to Polly, Alexa learned how to whisper and change the pitch of her voice earlier this year.