Amazon Polly turns text into speech. This allows you to create apps that talk and create new types of speech-enabled products. The Text-to-Speech service (TTS) by Polly uses advanced deep learning technology to synthesize natural sounding human voice. You can create speech-enabled apps that work in many countries using dozens of realistic voices from a wide range of languages.
Amazon Polly also offers Standard TTS voices. However, Neural Text-to Speech (NTTS), voices are available that offer advanced speech quality improvements through a machine learning approach. The Neural TTS technology of Polly also supports two styles of speaking that will allow you to better match your application's delivery style to the speaker: a Newscaster reading style, which is best suited for news narration use cases; and a Conversational speaking style, which is ideal to facilitate two-way communication such as telephony applications.