Amazon Polly Adds New Whispered Voice Tag, and Speech Marks for Synchronization w/Visual Animation

Опубликовано 19 апреля 2017, 20:06

Learn more about Amazon Polly at - amzn.to/2pgs2fU.
Amazon Polly is a service that turns text into lifelike speech, making it easy to add voice to your website, mobile app, or device. You can add high-quality male or female voice output to your video, presentation, or online training course, by example, with 47 lifelike voices across 24 languages.

To enhance the lifelike experience of using Amazon Polly voices, you can now easily add a whispered speech effect in your Text-to-Speech output. To create voices that mimic the effect of whispering, you simply use the SSML tag “whispered” to mark the text input to be spoken in a hushed or whispered voice. This tag can be applied to any of the 47 voices in Polly’s Text-to-Speech portfolio.

In addition to content creation, Amazon Polly now enables developers to provide speech-synchronized facial animation or karaoke-style word highlighting. Through the use of Speech Marks, you can add an enhanced visual experience to your application through synchronized speech. This is particularly useful if you have an application with an animated avatar – say, a gaming application -- which requires the ability to synchronize lips with voice, or you are using Polly in an educational environment, highlighting text for an enhanced reading experience. When used in combination with the synthesized speech audio stream, Speech Marks enables you to build applications that leverage the exact timing of when particular sentences, words and sounds are being produced, for a more engaging and animated experience when interacting with your voice-enabled application. You can try both new features through the Amazon Polly console.