I wonder if your use case is a bit different. Any chance that you are doing (wanting to do) something more along the lines of a recorded lecture, where you want the camera on you part of the time, and on a presentation / PowerPoint / slides / etc. part of the time?
If so, you may want to look into something like OBS (Open Broadcast Studio). This software allows you to set up different “scenes” and switch among them in real time as you are either recording or streaming. I use OBS when I am generating recorded lectures for classes; I have it set up so that I can set various “hot keys” to switch from just showing me in the camera, to showing just the presentation screen, to showing me in a small window in the corner of the presentation screen, and so on. Often I will have several different “presentation screens” that I need to switch among - a PowerPoint, a website, maybe a text document, etc. Occasionally I have set up with more than one camera.
Of course, I may be totally off-base in what it is you are wanting to do, but when I read your question I was picturing using OBS to record yourself talking, then switch over to a PowerPoint to generate the side-by-side comparison, then switch over to something else …