Come on man, seriously - the two communication modalities are completely incomparable.
Clearly the information traveling around on the phone network couldn't possibly be the same as the low bandwidth vibrating strings used in face to face communication. Obviously.
The internal communications of the mind have no need for such constraints (and evolved hundreds of millions of years beforehand).
Anyway, I don't know what you were actually trying to argue here: you just built a simulated brain out of people, and the massively multi-agent distributed nature of the language of that machine is (emergently) incomparable with vocalised language.