I don't want to say it's certainly not available, but I doubt it. Maybe someone has done something trying to recognize different voices by differences in pitch/volume/...
The vision pro has six mics, which likely enables it to locate the sources of sound in space by the amount of time it takes a sound to reach each mic (i.e. acting as an "acoustic camera"). Tablets and phones aren't going to have that hardware unfortunately.
And yeah, obviously wearing a headset is a pretty big compromise that's not always (or maybe even often) going to be worth it. This was more of a though of "the hardware can probably do this cool thing for people already using it" than "people should use the hardware so it can do the cool thing".