Everyone Has a Voice

Small thing, enormous effect, and almost nobody knows it is here: the characters can talk out loud, and they do not all have to sound the same.

Craft can read dialogue aloud. Left alone, every single character inherits the Game Master's voice — so your entire cast is one person doing all the parts, which is fine for an audiobook and terrible for a world.

What happens instead

Characters are cast when they are created, the same moment they get a name. The world picks a voice pool once, at installation, and then each person is matched inside it on gender and rough age.

Here is the clever bit

The pool is chosen for sound, not for nationality.

The voices are organised by real language because that is how the models were trained — but casting a Finnish voice for your dock crews is not saying they are Finns. It is saying their vowels sit forward and their consonants are soft. It is a decision about timbre, exactly the way an author picks a name for how it sounds rather than where it is from.

And if your world has two tongues — a settled one and a hill one, a court register and a dockside one — cast them from two different pools. The divide becomes audible before anybody explains it. Players hear the difference between two groups before they are ever told there is one.

What it does not do

It does not change how anyone talks. Accent, dialect, verbal tics, whether somebody trails off or talks over you — that is all separate, and it runs whether or not a voice is ever assigned.

This is purely the sound of them. And blank is a real answer: a world that wants one narrator throughout is not misconfigured, it is just a different kind of book.