A while back Microsoft demonstrated a translation technology which can translate your words into a different language in your own voice. I suppose technically we can analyze voice recordings of actual actors to obtain a voice profile with which we can use to do text to speech (not suggesting plotagon should do that, just saying technically we can do it since the technology's feasibility has been demonstrated)?
edit: also, there are already vision-based behavioral/gait analysis software in existence (how well they work is another question)...so conceivably we can also recreate an actor's performances?
About 10 years ago or more I read about a "vocal font" project. Where singers voices were samples and a vocal font of sorts was created which would be used to compose music digitally in the sound of any artist. From what I recall it was in development and they were far along. About once a year I try a google search but I have never been able to track it down again.
http://blogs.technet.com/b/next/archive/2012/11/08/microsoft...
edit: also, there are already vision-based behavioral/gait analysis software in existence (how well they work is another question)...so conceivably we can also recreate an actor's performances?