Send live audio or live transcripton to api endpoint

I want to get the live audio or live transcript while in the meeting. But then I don’t want to send the transcript back to the Zoom meeting. Instead, I would like to send the transcript to another server. Can I do that with the Closed Caption API, or do I need any other technology?

I already looked up Closed Caption API Doc which tell about how to use it to send the transcripted text back to zoom meeting.

I heard about Video SDK. I do not understand this. But looking for a solution.