On occasion I've used Otter or Whisper with some success.
Please let me know if you open source any of your work.
Do you transfer the files to your computer? Do you ever/often listen on the VoiceTracker? How do others respond to you making recordings? Do you organise the recording files into folders? Use filesystem tags (KDE Dolphin, etc) or symlinks? Ever have files on the computer that you needed when you're out (with the phone)?
How well do Otter and Whisper transcribe? Do you edit the transcriptions? How do you store the transcriptions? Do you ever search them? Do you store additional notes alongside the transcriptions and audio files?
Do you ever bookmark specific files? Specific timestamps in files? How long is your typical voice recording? How long are the 98th percentile long ones? How many recordings do you produce on average (per day, week, month)? Do you ever erase recordings?
What type of recordings? Reminders of things that are time sensitive (e.g. appointment dates)? Things for long-term archival (e.g. records of automotive maintenance)? Use it to assist in habit changing (recording diet) or mental health?
Yes, I intend to place the project on GitHub, probably GPL. Though I might consider MIT, I would actually love if somebody took off with it and made a business. I'd be a customer!
I've been recording to myself voice notes for years. Until now they've seemingly been near-read-only. The friction for recording them is often low (in settings where I can speak freely) but getting the information out of them has been difficult.
I'm now writing software to help me quickly get information out of the voice notes. So they'll be useful to me too, not just to future historians who happen upon my hard drive. I would not be able to devote the time to this without AI, even though most of the code and all the architecture is my own.