Voice typing saved my keystrokes. It didn't save my focus.

I've worked around speech technology for years, so I've probably tried voice input more than the average person.

And there's one thing that keeps bothering me:

Most voice tools remove the typing — but leave all the interruptions around it.

I can dictate a sentence.

Great.

But five minutes later I'm still stopping what I'm doing to open Reminders, find Calendar, switch to Messages, search for someone, click through menus, and then figure out where I was before all of that.

That's the part we're trying to push further with Loqua.

We're moving from voice typing → voice agent.

One example:

“Remind me tomorrow at 3 PM to send the Q4 draft, and open iMessage to tell Sarah I'm running 10 minutes late.”

Say it once.

The reminder is created.

iMessage is opened with the right person and message.

And you keep working.

The thing I'm most excited about isn't “voice control.”

It's reducing the gap between intention and action.

Because sometimes the hardest part of a tiny task isn't doing it.

It's starting the chain of clicks required to make it happen. 😭

We're calling this idea Zero Switch for now:

Stay in the task. Let Loqua handle the app hopping.

Does this feel genuinely useful to you, or does it still feel like a gimmick?

And if you could hand off one annoying desktop action to voice today, what would it be?