Record > caption > extract > use for training

I’m looking for some software advice, and potentially Hardware as well as I try to solve some training requirements. I need to be able to spin up an employee in under two weeks on some technology. So I am envisioning interviewing our current subject matter experts. I will record these meetings and try to extract the captioning. Once I have the captioning, I wanted to use an AI bot to help me create a training manual. I have zoom and I know it can caption. But I’m not sure about the extraction capability. Do you guys have any recommendations?