We’re excited to announce the general availability of Amazon Polly voices in the Alexa Skills Kit. Now you can use 27 different Amazon Polly voices to make your Alexa skills more engaging for customers. You can use the voices in your skills for free in all locales supported by Alexa.
Amazon Polly is a service that turns text into lifelike speech, allowing you to create applications that talk and build entirely new categories of speech-enabled products. Amazon Polly uses advanced deep learning technologies to synthesize speech that sounds like a human voice. Visit the Amazon Polly product page for more information.
Using Amazon Polly, you can choose a different voice for any utterance by using the Speech Synthesis Markup Language (SSML) and specifying an Amazon Polly voice using the “voice name” tag and the “lang” tag (if you need a language other than the default language for the skill). You can even use an Amazon Polly voice for every utterance in your skill. Developers are already taking advantage of Amazon Polly to:
Use Different Voices for Different Characters in Game and Story Skills
"As voice-first narrative game makers, building interesting, believable characters is at the center of what we do. The new Amazon Polly voices enable us to have more and better characters for our upcoming launch title, The Vortex,” said Jeferson Valadares, CEO and Co-founder of Doppio Games.
“The personality of our game’s AI assistant is critical to the gameplay experience of My Spaceship, which we expect to launch later this month,” said Sam Read of Robot Radio. “Using Amazon Polly, we were able to give our main character a voice that felt right for the personality we had crafted. The whole Robot Radio team were really impressed by how simple it was to implement; just a few extra SSML tags were needed to make My Spaceship feel like the premium experience we wanted to deliver.
Reduce the Time and Cost Required to Hire Voice Actors
“Amazon Polly has provided us a way to add many different characters and personas to our Angel Investor skill in seconds with the simple addition of an SSML tag,” said Gal Shenar, Founder of Stoked Skills. “As our skills constantly grow and evolve, it isn't feasible to hire voice actors at every increment. Amazon Polly voices allow us to provide the experience we want with almost no additional effort. Some of the voices are so good that people have even asked us who did the recordings!”
“Long SSML audio tags and Amazon Polly have proven essential for a weather information skill that we are developing for a Federal agency in partnership with a leading Federal contractor", said Pat Higbie, Co-founder and CEO of XAPPmedia. “Skill users can request dynamic weather content for more than 18,000 locations throughout the US and we rely on Amazon Polly within SSML tags to deliver responses that can run up to 4 minutes long. We are also using Polly lexicons to properly pronounce the technical jargon that is laced throughout the content and the users are able to select either a female or male voice and adjust the speed faster or slower. There is more to this skill than meets the ear and Amazon Polly handles the complex responses with extremely low latency."
You can use Amazon Polly voices in your skill today by simply adding SSML tags. Learn how in our documentation, and try all 27 Amazon Polly voices. Please review and follow these user experience guidelines for using Amazon Polly in your skills.
Bring your big idea to life with Alexa and earn perks through our milestone-based developer promotion. US developers, publish your first Alexa skill by October 31, 2018, and earn the new Echo Dot. Publish a skill for Alexa-enabled devices with screens and earn an Echo Spot. Publish a skill using the Gadgets Skill API and earn a 2-pack of Echo Buttons. If you're not in the US, check out our promotions in the UK, Germany, Japan, France, Australia, and India. Learn more about our promotion and start building today.