Need a quote for a human-entered closed caption feature

I’m trying to build a secure video comm platform for the Radical Telehealth Collective (RTC), a group of doctors and other health advocates working to provide free remote health care to folks in the USA who lack access. While I do have a modest budget to work with, I am asking you to consider donating some time and expertise, given the work we’re doing (all of my time on this project is given freely, FWIW). Just let me know what you’re comfortable with.

I need to know what it would take to build closed captions entered by a person, as an accessibility service for people seeking care. The idea is that the RTC will contract out to professional captioners for each call, so we need a UI for the captioner to use, and obviously we need to be able to display captions on the screen for all participants.

I have installed Jitsi and Jigasi from their Debian packages, and that’s as far I’ve gotten. I am comfortable on the command line but I’m not familiar enough with Jitsi to know where to go from here. Ideally what I’d get out of this is an understanding of the process so I can stand up a new Jitsi instance on a production server myself (the current one is just a proof-of-concept) and maintain it. If that’s too much to ask, working directly on a production server is great too.

What I’d prefer to do is jump on a quick call to answer any questions you have about the requirements, get a quote, and go from there. Thanks!