I could produce the output of an audio file but it came as a JSON type of file. I was informed that it is possible to configure the API to produce the file as .srt or .vtt which are adequate for being used to subtitle a video. It seems that the API has a parameter called "output_format" that controls the property of the file it delivers. However, I am unable to find the route to configure such parameter.
I did a lot of searching an even asked Bard, to no avail