What's actually stopping you from using voice dictation for real work?

I've watched a lot of people try voice dictation, get a good demo, and then quietly go back to their keyboard within a week. I did it myself for years.

For me the breaking point was always the cleanup. I'd talk for thirty seconds, get a transcript that was mostly right, and then spend the next minute fixing capitalization, adding punctuation, deleting the "um, no wait, actually" parts, and reformatting it into something I'd actually send. By the time I was done editing, typing would have been faster. So the dictation never stuck.

That's the thing I think most voice tools get wrong: they optimize for an accurate transcript, when what I actually want is finished text. Those are not the same problem. A transcript is done when the words are correct. The work is done when the right result is in the right place - clean prose in my editor, the reminder in my calendar, the paragraph rewritten the way I asked.

I've been building Juno around that gap (free, local, Mac), so I'm obviously biased. But I'm genuinely curious where everyone else lands, because I don't think cleanup is the only reason people bounce. The other ones I hear:

• Privacy - "I'm not sending my voice and everything I say to someone's cloud."

• Latency - the half-second lag breaks your train of thought, so you stop trusting it mid-sentence.

• Context switching - having to dictate in one app and paste into another.

• It just feels weird - talking out loud at your desk, especially in an office or a shared space.

• Accuracy on the stuff that matters - it nails the easy words and fumbles the client's name, the URL, the one date you actually needed.

So, honest question for the room:

What's the actual reason you don't dictate more than you do? Is it one of these, or something I haven't named? And for the people who did make it stick - what finally got you over the hump?

I'll be in the comments all day.