Text-to-speech (TTS) synthesizes spoken audio from written text and underpins how screen readers communicate page content to blind and low-vision users. It is also used independently as a reading support tool by people with dyslexia, other reading disabilities, or those who simply find listening easier than reading dense text.
For TTS to work well, underlying content needs correct reading order, properly expanded abbreviations where pronunciation matters, and text that is real, selectable text rather than an image, since an image of text has no words for TTS software to read aloud.