Face tracking has existed for years now. I frankly don't see what's different between what you described and FaceRig.
I want a model which is made photoreal with my own image, so it can be given a voice in real time with my words, but a filtered version of my facial expression and pose.
So how I look and act is essentially scriptable.
https://www.technologyreview.com/2023/09/19/1079832/chinese-...
https://www.technologyreview.com/2024/05/07/1092116/deepfake...