macOS
Lulucat Speecho
Hold a key down. Speak. Release it.
Dictation that finishes where you were already typing
Lulucat Speecho transcribes your speech while you keep the right Option key held down. Words appear in a panel along the bottom of the screen as you talk; release the key and the final text is pasted at the cursor — in a message box, code editor, search field or whatever app had the focus. There is nothing to open beforehand and nothing to copy afterwards: the sentence you have just spoken is already in the document you were writing.
The complete interaction
One key, held down, handles everything.
Hold to speak
The right Option key starts a dictation when it goes down and ends it when it comes up. It works in every app because the system watches the key across the whole system, rather than tying it to one window. The left Option key is untouched, so the special characters and shortcuts it types continue to work as they did before.
Words as you speak
Audio is streamed for transcription while you are still talking, so words turn up shortly after you say them, not once you stop. Text the model has confirmed is shown at full contrast; text it might still revise is grey, so you can see straight away which part has settled.
Release to paste
Release the key to end the stream; Speecho waits for the last words to be finalised, then pastes the result at the cursor. The text travels through the clipboard, whose previous contents are restored a second later, so anything you copied earlier is still there when you need it.
Cheap to abandon
A press too brief to contain speech is discarded, as is a take where another key was pressed — that means someone is typing a special character, not dictating. Nothing is pasted either way, so a mistaken press costs nothing and leaves nothing to undo.
Languages
Supports more than 60 languages, automatically recognizes the language being spoken, and handles multiple languages in the same sentence.
The panel while you talk
The panel appears at the bottom of whichever display the pointer is on, above full-screen apps and across every Space. It never takes focus, so the text field you were using stays active and the caret remains where you left it. A waveform on the left moves while audio is sent and changes to an amber colour while the last words are being finalised, making a microphone that is capturing nothing visible in the first second rather than after the event.
Two system permissions
macOS asks for microphone access before it records any audio. Accessibility supplies the other half: watching a modifier key outside the app and pasting into whichever app has focus. Both permissions are explained when they are requested, and the app keeps showing which one is missing until you grant it, including where to find it in System Settings.
What leaves the Mac
While you hold the key, audio is sent for transcription and nothing else is uploaded. Recordings never touch the disk. The recent-dictations list lives in memory for the current run only and disappears when you quit. There is no account to create and no analytics.
Availability
Speecho is still being built and has not been released. It will need macOS 15 or later and will be distributed from this site rather than the Mac App Store: pasting text into another app is not allowed by the App Store sandbox, and that is the part of Speecho worth having.
Email support@lulucat.ai if you would like to know when it ships.