Audio to text - Firebase Storage or Cloudinary

Hi,

I have been working on a small game and I want people to be able to upload a short (5-10sec) audio recording which is then converted into text. I can use speech to text for this, but I don’t like the way the person needs to go silent before this is uploaded. I want the timer to cut them off and upload just the 5 secs they were talking for. I have set up firebase storage with the google audio to text add on, but I am struggling to figure out how to upload an audio from thunkable to firebase storage (I can do realtime database, but not storage bucket). I was wondering if cloudinary is an option. I am fairly new to all of this, but I have been learning fast, and I don’t have a coding background, so sometimes the lingo confuses me and I thank everyone for their pateince when answering my questions.

If anyone can help or has some useful advice so that I don’t waste too much time, that would be amazing.

Cloudinary is definitely an option here!
Screenshot 2023-11-30 at 3.19.57 PM

Thanks matt. Ive been looking into this more today. I havent yet worked out how to make the transformation work within cloudinary, but im getting closer. If you have any advice as to how to automate the transcription that would be amazing

Ok, ive figured out how to upload the 5 sec recodording and cloudinary now transforms that in to either an srt, vtt or .transcript file. But i dont know now how to extract that back into thunkable. Do you know how i would display any of these file types in thunkable?