Writing a task down is itself a task.
The thought arrives while you are doing something else: the report is overdue, the dentist needs booking, there was a form. Getting it into an app means a name field, a date picker, a duration, a category. Four decisions to store one thought, and somewhere in the middle of them the thought is gone and so is the reason you picked up the phone.
Talk once. Sort it out afterwards.
Edit, deselect, or move.
One mic, and an obvious way out.
The opening screen says "Drop your thoughts," and under it, "Say everything on your mind. We'll pull out tasks." That is the whole instruction. There is no format to follow and no example to match.
The line under the mic is the largest piece of guidance on the screen, and it says exactly one thing: tap the mic to start. It used to say "3 minute max per recording," a constraint set in the smallest type on the page, telling you about a ceiling almost nobody reaches instead of telling you what to do. That was worth fixing, because a bare circle with no label is not an invitation, and people arrived at this screen and left without touching it. Underneath sits "Type it instead," which is not a fallback so much as an equal door: the typed text goes through the same parsing and lands on the same results screen. If the mic is unavailable, or you simply do not want to talk out loud on a train, nothing about the feature is lost.
A dictation button that drops raw text into a title field has moved the typing, not the work: you still have to split what you said into separate tasks, set each date, and file each one. Voice capture does that part. And it deliberately stops short of the last step, because an app that silently created four tasks from something you half-said would be worse than one that made you type. So it shows you what it heard, lets you correct all of it, and waits. The confidence to talk freely comes from knowing nothing is committed until you have seen it.
Capturing is the start of it.
Getting a task onto the list is one problem. Beginning it is the other one.
One question, then you're going.
A captured task still has to be begun. Just Start is one question about how it feels, and the first sixty seconds are the whole goal.
Too big to start? Break it down.
Some of what you say out loud turns out to be five things wearing a trench coat. Breakdown splits it and hands you the first piece.
What you did, counted kindly.
Starting counts, not just finishing. Resets at midnight, and past days are never stored.
Voice capture, in plain answers.
How does voice capture work?
Tap the mic and talk. You can list several things in one go, in whatever order they come out. Beginary transcribes as you speak, then pulls the tasks out of what you said and sorts them into going to today, upcoming, and saved for later. Nothing is saved until you look at the result and tap the confirm button.
Does it understand dates and times?
Yes. Say "book the dentist tomorrow at three" and the date and time arrive already filled in, on editable chips you can tap to change. It also notices when you mention that something is overdue and tags that item so you can see why it was put where it was.
What if it gets something wrong?
You fix it before anything is saved. The results screen exists for exactly that: tap a name to edit it, tap a time chip to change it, tap Move to send an item to a different group, or untick anything you did not actually mean. The screen tells you so in its own words: "Here's what I heard. Edit, deselect, or move."
How long can I talk for?
Up to three minutes, which is far longer than anyone speaks in one go. The screen shows the elapsed time as you talk, warns you gently as you approach the limit, and makes your plan automatically if you reach it. You can also tap the mic to wrap up early whenever you are done.
Can I type instead?
Always. "Type it instead" sits under the mic on every state of the screen, including when the microphone is unavailable or permission has been declined. Typing goes through exactly the same parsing and the same results screen, so nothing about the feature depends on being able or willing to talk out loud.
Why is capturing by voice easier?
Because typing a task is itself a task. A form with a name field, a date picker and a duration is four decisions at the moment you are trying to offload one thought, and for a lot of ADHD adults that friction is where the thought is lost. Speaking has almost no start cost, and it holds several things at once in the order they actually occurred to you.
Say it before you lose it.
Join the waitlist for early access. We'll send one email when it's ready. That's it.
No spam. No streaks. Unsubscribe anytime.