Text-to-Speech, or TTS, is a form of speech synthesis that converts written text into a spoken voice output, or speech. Text-to-speech allows a computer, device, or application to speak by giving it a voice.
Text-to-speech was originally used to improve the accessibility of computers. This allowed visually impaired people to listen to digital content that they were originally unable to read. It was also used to give a voice to people who lost their own (see Stephen Hawking). Since then, text-to-speech has been used in medical devices, announcement systems, emergency alerts, eLearning software, IVR telephony systems, and many other products.
Today, demand for text-to-speech has grown rapidly. By combining text-to-speech and speech recognition, people are able to interact with technology like they would with another person, by having a conversation. This creates a completely hands-free user interface which breaks down the barriers between human and machine interaction.
Well-known examples of this include Apple's Siri and Amazon's Echo. Text-to-speech technology is becoming a big part of the technical world and will soon be a big part of our daily lives.
For an in-depth looks at how a text-to-speech engine and voice is made, read What Is Text-to-Speech And How Does It Work?
Everyday Uses of Text-to-Speech
Discover some of the everyday uses of text-to-speech technology in this short video as it follows Marcy, a young woman who uses TTS throughout her day to commute, learn, and interact with technology.