What is TTS (Text-to-Speech)?

TTS, an acronym for text-to-speech, is speech synthesis technology that converts written text to spoken words. It synthesizes words, rather than playing back pre-recorded messages. This can be difficult with the English language because many words are spelled the same, but have different pronunciations and meanings. For example, TTS must figure out if it should pronounce the word "lead" as it's pronounced in "lead the way" or as it's pronounced in "lead pipe." This is handled by calculating probability and choosing the most likely pronunciation. It's an imperfect approach and there are mispronunciations.

TTS was originally developed as assistive technology for the visually impaired to help them understand, for example, website content. TTS is now a common feature of websites and popular applications like Microsoft Word. There are several TTS software providers and the TTS functionality can often be incorporated into websites and applications using a simple API. TTS is becoming more mainstream as everyday users use it for activities like reading inbound text messages out loud.

TTS in contact centers

TTS has some interesting applications in contact centers and its innovative use will likely expand. Interactive voice response (IVR) systems can use TTS to provide customers with information such as account balances and how much is due from their latest bill. IVR systems can use TTS to have callers confirm what they entered into the IVR, such as a customer ID. TTS can also be used for administering post-call satisfaction surveys. Organizations just need to type in the questions they want to ask, and the system will synthesize the speech for them. This adds flexibility to businesses that want to change-up their survey questions.