Hi,

I have been trying to achieve a speech-to-text conversion of recorded audio (from an audio input field).

I tried using Google Cloud Speech-to-Text API, but I am not getting a proper API response from that. I also tried doing this through a python script that is hosted online, but again I am not getting a proper response API for that.

Please let me know if you have any suggestions on how to achieve this. Please note that the processing needs to be done in the background (through a workflow deluge script), and it is not feasible to first download the recording and then process it separately.

Any help on this would be deeply appreciated