~jheckt/audio-notes

Code I use on top of Whisper to manage my audio notes.
renamed config to example.config.json so it doesnt hork up installs
added summarize and summarize_char_min to config file

refs

main
browse  log 

clone

read-only
https://git.sr.ht/~jheckt/audio-notes
read/write
git@git.sr.ht:~jheckt/audio-notes

You can also use your local clone with git send-email.

#Audio-To-Notes

This is a simply "daemon" that checks a given directory for new audio files, transcribes the english out of them with OpenAI's Whisper, then saves the text and audio. It was created so that I could easily dump audio notes to my NAS and "set it and forget it".

#Requirements

Whisper from OpenAI:

pip install git+https://github.com/openai/whisper.git 

As well you will need FFMPEG, which the Whisper docs have instuctions for.