Special text-to-speech synthesizers exist and allow users to create an audio file (for example .mp4 file) made of computer generated speech from a text saved in a document, something that text to mp4 conversion might represent.
Such programs are unfortunately pretty expensive and even these are not perfect. In most cases manual tweaking during the process because otherwise the audio would not b perfect. Other than that, you most likely wont find a "simple" text to mp4 converter.