Hey, Gordon.
While I’m certain that it’s possible to do what you’re asking about, I think that you’re going to find some challenges that may be quite difficult for a ‘beginner’ to get past. For example, in order for you to be able to use some sort of commands to tell your model how to pose and what to “say” at any given time, you’re going to need some sort of 3D interface, and that interface will need to be compatible with your model (or, more accurately, your model will need to be compatible with the 3D interface you’ll be using). Once you get that part taken care of, you’ll need to work out some means of giving your chatbot’s motion some sort of context to her output. After all, you don’t want your chatbot to shake her finger angrily when she’s making a joke, do you? Of course, you’ll also need to have some way to synchronize her text output to her facial movements, giving her realistic “visual speech”, as well. These are all very challenging tasks, even for someone who’s experienced in such matters, and is quite likely too much for a beginner to do all at once; but it is possible. It would just take a lot of time, and require learning a LOT of new skills, and will require obtaining software you most likely don’t have yet.