Now Alexas voice apps dont have to sound like Alexa. Amazon today is offering a way for developers to give their voice apps a unique character with the launch of eight free voices to use in skills, courtesy of the Amazon Polly service. The voices are only available in U.S. English, and include a mix of both male and female, according to Amazon Pollys website. Amazon Polly was first introduced at Amazons re:Invent developer event in November 2016, and has been steadily ramping up its capabilities in the time since. The text-to-speech service today is capable of things like whispering, speech marks, using a timbre effect, and dynamic range compression – all which make the voices sound more natural. While the speech engine today supports a couple dozen languages, only the U.S. English voices are being offered to Alexa developers at this time. But their addition could make some of Alexas skills more engaging – especially those involving different characters, like an adventure story or game, for example. Developers today may already be using multiple voices in their skills, but the process of doing so is more cumbersome and rigid, as with mp3 file uploads. To use an Amazon Polly voice instead, developers would use Structured Speech Markup Language (SSML) and then specify which voice they want with the voice name tag. This makes it easier to adjust what is said, as developers could just change the text instead of having to re-record an mp3. Amazon has been working to make Polly more accessible to a wider audience, recently by offering a WordPress plugin that could turn your posts into podcasts. The new Alexa skills integration, meanwhile, gives Polly another avenue of reaching consumers. Its also another means of competing with Alexas rival, Google Assistant. At Googles developer conference last week, the company announced six new voices generated by Wavenet, including one from singer John Legend. These will roll out later this year, and presumably, could make their way to the Assistant developer ecosystem as well.
You won't have to hear the same voice in every app. Do you wish Alexa would respond to your commands with different voices? You'll get your wish soon. Amazon has released a developer preview that lets Alexa skill developers use a selection of voices from Polly (Amazon's text-to-speech service). An adventure story can give each character a different voice, for instance. Creators could already 'hack' additional voices in through MP3 recordings and similar techniques, but this is decidedly more elegant. The feature currently only allows using eight US English voices (Polly supports roughly two dozen languages), and it should take a while before multi-voice skills arrive. However, the timing couldn't be much better. Google just added six voices to Assistant. While this clearly isn't the same (many skills will just use whatever regional voice you have), it should lead both to some basic variety and voice apps that are considerably more complex.