This API has speech-synthesis capabilities to synthesize text into natural-sounding speech in a variety of languages, accents, and voices. The service supports at least one male or female voice, sometimes both, for each language. Audio is streamed back to the client with minimal delay and includes a method that synthesizes text to audio over the WebSocket protocol. The call supports plain text and SSML input, including the element as well as word timing information for all strings of the input text. IBM Watson can understand all forms of data, interact naturally with people, and learn and reason, at scale.