Polly will let skill developers choose from eight different English voices and a wide variety of non-English voices. For developers with skills that use only one voice, changing it or adding another in the right place may offer a more engaging experience for customers, according to the post. Polly uses advanced deep learning technologies to synthesise speech that sounds like a human voice.
If you already use multiple voices in your skill via using.mp3 files or another technique, consider Amazon Polly for its natural-sounding voices and ease of maintenance.
This means that developers can now customize voice apps using eight unique voices other than that of Alexa. With this feature, users can tell Alexa to remember a specific thing and recall that information at a later date. You can cache and replay Amazon Polly's speech output to prompt callers through interactive voice response (IVR) systems, such as Amazon Connect.
Polly's voices are far from ideal, of course, but as they see more use, that could change. Skills that drive high customer engagement can also lead to a payday for developers through Alexa Developer Rewards. Amazon Polly can generate speech in dozens of languages, making it easy to add speech to applications with a global audience, such as RSS feeds, websites, or videos.