Comment by maxkfranz
10 days ago
Yeah, it’s not going to compare to Codex-5.2 or Opus 4.5.
Some non-programming use cases are interesting though, e.g. text to speech or speech to text.
Run a TTS model overnight on a book, and in the morning you’ll get an audiobook. With a simple approach, you’d get something more like the old books on tape (e.g. no chapter skipping), but regardless, it’s a valid use case.
Which TTS would you suggest? Anything out there that is able to properly see/handle modulation, punctuation and overall sentence 'mood'? I've been looking for something easy to set up but most is either extremely complex or is producing output of relatively poor quality.
I’m still experimenting with them. I suspect you may have to do only one paragraph at a time and concatenate them together. Let me know if you’d be interested in collaborating, as I’m interested in this use case too.