AWS Machine Learning Blog
New Developer Preview: Use Amazon Polly voices in Alexa skills
Listen to this post Voiced by Amazon Polly |
Amazon Polly is a service that turns text into lifelike speech. Using Amazon Polly you can create applications that talk and build entirely new categories of speech-enabled products. Starting today, you can apply to participate in a developer preview that allows you to use eight English (U.S.) Amazon Polly voices to narrate your Alexa skills.
If your skill uses only a single voice today, you can try changing the voice or adding different voices in the right places to provide an even more engaging experience. Developers in the preview can select a different voice for any utterance by constructing output speech using the Structured Speech Markup Language (SSML) and specifying an Amazon Polly voice using the voice
tag for free in Alexa skills. Note that SSML tags that are only available through the Amazon Polly service and not through Alexa skills will not be available when you use this new capability.
Out of the eight English (U.S.) Amazon Polly voices, five are female and three are male voices. The eight voices are: Ivy, Joanna, Joey, Justin, Kendra, Kimberly, Matthew, and Salli.
This capability enables developers to give their Alexa skills specific Amazon Polly voices. The example below shows Kendra being specified for part of the response to make the complete response sound like a dialog with two voices.
Example:
Listen now Voiced by Amazon Polly |
If you are already using multiple voices in your skills with .mp3 files or other audio files, consider using Amazon Polly for its natural-sounding voices and ease of maintenance. Apply today to join the preview and use Amazon Polly to voice your Alexa skills.
About the Author
Woo Kim is a Product Marketing Manager for AWS machine learning services. He spent his childhood in South Korea and now lives in Seattle, WA. In his spare time, he enjoys playing volleyball and tennis.