macOS
Lulucat Speecho
Keep a key held. Speak. Release it.
Dictation that ends at the place you were already typing
Lulucat Speecho transcribes speech while you hold the right Option key. As you talk, the words appear in a panel at the bottom of the screen; when you let go, the completed text is pasted at the cursor — whether that is a message box, a code editor, a search field or another focused application. Nothing needs to be opened first, and nothing needs to be copied afterward: the sentence you just spoke is already in the document you were writing.
The interaction from start to finish
Keep one key held down and it handles the whole exchange.
Hold to talk
The right Option key begins a dictation on the downstroke and ends it on the upstroke. It works across every application because the system observes the key globally rather than binding it to one window. The left Option key is left alone, so its special characters and shortcuts continue to work as usual.
Text as you speak
Audio streams to transcription while you are still speaking, so words arrive shortly after you say them instead of waiting until you stop. Confirmed text appears in full contrast, while text the model may revise appears in grey, making the settled portion clear at a glance.
Let go to paste
Releasing the key closes the stream, waits for the final words to be finalized, and pastes the result at the cursor. The text passes through the clipboard, and the previous clipboard contents return one second later, so what you copied earlier is still available when needed.
Nothing to lose
A press too short to contain speech is discarded, as is a dictation during which another key was pressed — that indicates someone is entering a special character, not dictating. Neither case pastes anything, so an accidental 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 as you talk
The panel sits at the bottom of the display where the pointer is, above full-screen applications and on every Space. It never takes focus, so the text field you were using remains active and the caret stays where you left it. A waveform on the left moves while audio is sent and shifts to an amber colour while the final words are being finalized, so a microphone capturing nothing is apparent in the first second rather than after the fact.
Two system permissions
macOS requests microphone permission before any audio is recorded. Accessibility provides the other half: monitoring a modifier key outside the application and pasting into the application with focus. Both are explained where they are requested, and the app continues to show which permission is missing until it is granted, including where to find it in System Settings.
What leaves the Mac
Audio is sent for transcription while you hold the key, and nothing else is uploaded. Recordings are not written to disk. The recent dictations list remains 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 in development and has not been released. It will require macOS 15 or later and will be distributed from this site instead of the Mac App Store: the App Store sandbox does not permit pasting text into another application, and that is the part of Speecho worth having.
Write to support@lulucat.ai to hear when it ships.