Amazon is introducing a new speaking style for Alexa and adding some speaking styles for other AI voices, the company said today. The longform speaking style is available for US developers who want a reading voice that sounds more natural when reading long pieces of content, like articles or podcasts.
Amazon says the longform style is “powered by a deep-learning text-to-speech model,” and allows Alexa-voiced devices to speak with more natural conversational pauses. It follows last year’s release of new speaking styles for news and music content and a November update that allows Alexa to seem “disappointed” or “excited.”
(I’ll be honest: the only obvious differences I heard between the two samples Amazon provided were longer pauses between sentences in the second sample).
Amazon also is adding its news and conversational speaking styles for the Matthew and Joanna voices from Amazon Polly, its neural network-based text-to-speech AWS service, and is adding its news speaking style to Lupe, its US Spanish voice.
Polly’s speaking style voices, which are available for a few voices, and 10 new Polly voices, are also available for developers to build Alexa skills. The new voices are available in six new languages.
UPDATED April 16th 11PM ET: Added information about 10 new Polly voices available.