Hello folks!
I am trying send an api call to open AI. Let me explain:
In my app, the user is able to record himself by pressing a button and stop the recording when another button is pressed.
Now I would like to send an API Call to whisper AI to transcribe the audio into text so that I can show it to the user on a screen page, or use it as text and combine it with other texts.
My goal is to call the API for transcriptions when the stop button is pressed, but how can I make sure the current recorded audio is being connected to the API call? I don't know if I need to assign a variable to it or what else?
This is my API call configuration:
I feel like I am almost there with the solution, please can someone help me in any way?