Published: Thu, May 17, 2018
Tech | By Dwayne Harmon

Alexa developers get 8 new voices via Amazon Polly

Alexa developers get 8 new voices via Amazon Polly

If you're bored of always hearing the same Alexa voice regardless of what skill you're using, this is likely the update you've been waiting for. So, for example, they can give a different voice to each character in an adventure story or in a game skill. This allows developers to create speech-enabled products, and apps that talk to users.

A team of Chinese and USA researchers has discovered a new method of attacking smart assistants like Amazon Alexa and Google Home, which they have named "voice squatting". Before this, developers were only able to add voices to their skills by uploading an MP3 file or by creating a custom audio track, which was quite painstaking.

Amazon is giving this choice to developers through their Polly text-to-speech service. You can even use an Amazon Polly voice for every utterance in your skill if you like. Amazon Polly makes it easy to request an additional stream of metadata with information about when particular sentences, words and sounds are being pronounced. Those who are not chosen for the preview will still receive information on using Amazon Polly voices in Alexa skills when it is available. The point of having access to multiple Alexa voices is so developers can build skills (apps) in which users interact with a variety of voices instead of just one.

Below are two videos demonstrating a voice squatting attack on an Amazon Alexa and Google Home device.

Like this: