Many years ago (at least two computers) I wrote a program using Python and Cepstral (a TTS engine) to convert text to mp3 files. I made a good start at “recording” all of Simplified Functional Edition 2, but didn’t finish it, and planned to offer the service to anyone with text files. Then I found a problem with the calibration, and life got busy. (Good, but busy.)
Does anyone want to take it over? Or redo it with a different language or TTS engine? Or whatever it takes to get a reasonably easy way to convert sound files to dictation files? Or learn more about how it works before deciding? I can consult, but I haven’t coded in years. I’m not stuck on Python or Cepstral, they were just the best tools I had at the time.
Email me at [email protected] or reply to this thread.