Example implementation

High level overview

You'd need 2 cloud function, one (createTranscript)to start the recognition, and trigger a cloud task that on a time delay triggers the second one (firestoreCheckSTT)to check the progress of the transcription gcp operation. If the transcript is not done, it triggers another cloud task to re-trigger the second cloud task later.

Cloud Function createTranscript

Cloud function to check if operation is done firestoreCheckSTT

missing handling edge cases, eg If the transcript has been deleted, should try to save in the cloud task, it should drop it Eg instead of set / merge should be try catch, with a method for update only if it exists

Last updated