Cloud Polly allows you to turn any text into realistic speech, allowing you to create a variety of multimedia content such as audiobooks, podcasts, voice content, as well as speaking applications, as well as create completely new categories of speech-enabled products. Cloud Polly's Text-to-Speech (TTS) service uses advanced deep learning technologies from leading cloud service providers such as Amazon Web Services, Microsoft Azure, Google Cloud Platform, and IBM Cloud to synthesize natural human speech. With over 630 different realistic voices in over 70 languages, you can create speech-enabled applications that work in different countries.

In addition to the standard TTS voices, Cloud Polly offers Neural Text-to-Speech (NTTS) voices, which provide improved speech quality through a new machine learning approach. Much of the Neural TTS Cloud Polly technology also supports cloud provider-specific unique speech styles that allow you to better align the speaker's speaking style with the application: Example: An announcer's reading style adapted to news storytelling use cases and a Conversational speaking style that's ideal suitable for two-way communication, such as telephone applications.

Enjoy conveniently using SSML tags to add a variety of voice effects such as adjusting the pitch, volume, speed, emphasis, beeps for words or phrases, etc. The complete list can be found in the demo by selecting the appropriate voices.