I just bought the software and it worked perfectly on the first run. It could use a few features, though.
- I'd like to be able to remove the ">>" at the start of lines.
- Recognition of audio gaps. The file I tried it on has no audio for the first 20 seconds, but it starts the subtitle at 0:00:00. It also leave t he subtitles up during gaps instead of going blank until the next speaking portion
- Hearing impaired subtitles, i.e. "[Music]" "[Screams]" "[Engine Sounds]"
- Batch queueing. I would like to throw in a more than one file and walk away while it works.
- The option to auto save to SRT.
Edit: I think I spoke to soon about how good this is at transcribing. I'm running into a problem where it's repeating text hundreds of times over.
The AI model really doesn't understand the stop and start of speech.