One thing Amazon has been trying to do with Alexa ever since it launched the AI assistant is make it sound more conversational. Today the company took a big step in that direction, rolling out emotions and new speaking styles for Alexa. These new features are launching for developers today, so we should see them added to various skills soon.
On the Alexa Skills Kit Blog, Amazon details these new emotions and speaking styles, which are powered by the company’s Neural Text-to-Speech tech. Alexa can now respond to queries with an excited or disappointed tone, both of which are available in three different intensities: high, medium, or low. For instance, when users are playing a trivia game and get an answer correct, developers might opt to have Alexa respond with a high-intensity excited tone, which can be heard below.
On the other hand, developers may want to use something like the low-intensity disappointed tone when Alexa is delivering bad news, such as a weather forecast that calls for rain or sports scores in which the home team lost. Check out a sample of that particular emotion below.
In addition to the new emotions developers can tap into, Alexa now has two distinct speaking styles that can be employed as well. One speaking style gives Alexa a news anchor type flair, which is obviously ideal for when she’s reading off headlines. The second speaking style is geared more toward music, making her sound like a radio DJ. Check out both speaking styles below, along with a sample of how Alexa would normally sound for comparison.
These new speaking styles are certainly cool, though after years of hearing Alexa’s robotic, usually unchanging tone, it’s definitely a little jarring to hear her speak with emotion or change things up depending on the content. Developers who are interested in implementing these speaking styles can find out how to do that in the Skills Kit Blog post linked above, while the rest of us will wait for Alexa to start sounding a little more animated.