Text To Speech

Text To Speech (TTS) is a type of general purpose technology (GPT) that allows users to input written text via a keyboard and get instant results that come in the form of speech. It works like this: The user types in a phrase or sentence and the technology will convert the text into speech which is spoken out loud. The accuracy and quality of the output depends on the TTS model being used. Generally speaking, the software converts the text into a language model – a set of rules about how words are pronounced.