I mean a text interface - it’s more like if you went to a restaurant and there was no menu so you had to ask the waiter everything, but he also spoke absolutely no English so you had type out your questions on your phone for him - the latency while the model collates the data is not good
With a well performing voice model I don't think it's going to be much different than ordering at a restaurant.
To be clear I'm not advocating for this and likely wouldn't use it myself but it seems perfectly viable for a certain kind of customer. Particularly those with decision paralysis that are spoiled for choice.