Text-to-speech is a research field and technological domain dedicated to the synthesis of audible speech from written text. It encompasses the study and development of computational methods, linguistic models, and acoustic signal processing techniques aimed at generating natural, intelligible, and expressive synthetic voices, investigating key characteristics such as speech naturalness, intelligibility, expressiveness, speaker identity modeling, and real-time performance. The significance of this field lies in its role in enhancing human-computer interaction, improving accessibility for individuals with print disabilities, and enabling automated content delivery across various applications.