Amazon Web Services has released a new service designed to convert text into realistic voice audio applicable to multiple languages.
The Amazon Polly service is available through the AWS GovCloud (US) Region, the company said Wednesday.
The text-to-speech service makes use of deep learning technologies to help users construct speech-enabled applications.
Amazon Polly’s API may be integrated with other applications to stream the converted audio in a variety of file types such as MP3, Vorbis and PCM.
The service is also compatible with lexicons and Speech Synthesis Markup Language tags that allow users to define pronunciation, volume, pitch and other descriptive factors for vocal speech.
The console for Amazon Polly may be opened here.