Text-to-speech (TTS) technology enables a user to convert a written text into computer-generated speech, transforming the way we interact with text and technology. Speech synthesis has evolved over the centuries from relatively primitive physical models of the human vocal tract to state-of-the-art neural network-based systems that accurately mimic speech with human emotion. TTS has become a powerful tool for language teaching and language learning. In this chapter, we discuss the technological evolution of TTS and its advantages and disadvantages in how it contributes to language learning.