I started playing the audio. I liked it. The text was right there matching what I was hearing. I just wish that it highlighted the word in the audio. I'd much prefer a tts version that does that, even if the voice quality is worse. There was a disconnect between my eyes and ears and it felt off.
good news: i already store the word level alignments, i just felt like words lighting up were distracting
i might add this as an option in the future, thanks!