Why can't users control captions?

[MeganClegg]

I'm new to using Zoom and I'm incredibly confused about the captioning features. Please help me make sure my understanding of the situation is right -

So users of Zoom can enable automatic captions in their account (I have a paid account and have done this.) However, if they join a Zoom call set up by a host (an organization or another user) that doesn't have automatic captions enabled, they cannot use them? They have to speak to the host to request they be turned on?

Is this correct? I'm having trouble wrapping my head around this. Captions have always been a single-user-facing, single-user-controlled experience on every other platform I've used.