Synthetic speech is a field of study referred to both as speech synthesis and as text-to-speech (TTS). It consists of generating speech synthetically, for example turning and as text-to-speech (Taylor, 2009).
Currently the main areas of focus of research in this field of study are to synthesize text into speech that is simultaneously intelligible, natural-sounding and also expressive (Dutoit & Stylianou, 2018).
References:
Dutoit, T., & Stylianou, Y. (2018). Text-to-Speech Synthesis. In R. Mitkov (Ed.), The Oxford Handbook of Computational Linguistics 2nd edition (2nd ed.). Oxford University Press.
Taylor, P. (2009). Text-to-Speech Synthesis. Cambridge University Press.