Audio and Video Transcription

[itsmcb]

Hi all,

I store many audio and video files with useful information in my Nextcloud. I occasionally manually create transcriptions of them using OpenAI’s Whisper model running on my laptop. It would be awesome if I could create a workflow with Nextcloud where audio and video files uploaded to a particular folder could trigger a transcription service to run (ex. OpenAI’s Whisper with parameters set by the user). It would also be awesome if the text could be accessed in the search function. While this is a bit of a niche use case, it’d help me out quite a bit

What do you think of this idea?

Thanks,
Martin