Don't get your hopes up too high. Dragon isn't that great, in my experience. I use it for prose text to help limit my typing, and I do spend a significant portion of the time frustratedly editing dumb mistakes that should obviously be something else from the context (wrong grammar or nonsensical combinations of words). Correcting and re-correcting and training and retraining words it keeps getting wrong is really frustrating. It may be that their NZ English model was built from a smaller corpus, so YMMV.

I'd rather not use a cloud service like Google.

You might be interested in this: https://github.com/biemster/gasr (not production-grade, but depending on your workflow you can hack on it)