I’m struggling to figure how i can utilise OpenAIs Whisper model to transcribe an audio file that I upload to a specific folder in SharePoint. I’ve got this to work by recording on a Power App but I would like to be able to record on any device, then simply save it a SharePoint folder and the audio be sent for transcription.
The trigger is a ‘When a file is created (properties only), I then retrieve the contents of the file using ‘Get file content’, i’m now stuck on how successfully pass this to Whisper. My HTTP request follows the format of a tutorial by Mohamed Faleel although this again is specifically for Power Apps whereas i simply want the trigger to be an uploaded file to a SharePoint folder so that i can record on another device.
Can anyone shed some light on how to achieve this, I’m truly stuck with the HTTP request and would love it if you could send through an example of how to get this to work.