macOS
Lulucat Speecho
Hold a key down. Speak. Release it.
Dictation that ends where you were already typing
Lulucat Speecho transcribes speech whilst you hold the right Option key. The words appear in a panel at the bottom of the screen as you speak, and releasing the key pastes the finished text at the cursor — in a message box, code editor, search field or any other application with focus. Nothing needs opening first and nothing needs copying afterwards: the sentence you have just spoken is already in the document you were writing.
The interaction in full
One key, kept held down, takes care of everything.
Hold to talk
The right Option key starts a dictation as it is pressed and ends it as it is released. It works in every application because the key is watched across the system rather than tied to a single window. The left Option key is left untouched, so the special characters and keyboard shortcuts it types continue to work as before.
Text as you speak
Audio is streamed for transcription whilst you are still speaking, so words appear shortly after you say them rather than once you stop. Text confirmed by the model is shown in full contrast, whilst text it may still revise is shown in grey, making it clear at a glance which part has settled.
Release to paste
Releasing the key ends the stream, waits for the final words to be finalised and pastes the result at the cursor. The text goes through the clipboard, and its previous contents are restored a second later, so anything copied earlier is still there when you need it.
Cheap to abandon
A press too short to contain speech is discarded, as is a dictation during which another key was pressed — that is someone typing a special character, not dictating. Nothing is pasted in either case, so an accidental press costs nothing and leaves nothing to undo.
Languages
Supports more than 60 languages, automatically recognises the language being spoken, and handles multiple languages in the same sentence.
The panel whilst you talk
The panel appears at the bottom of whichever display the pointer is on, above full-screen applications and on every Space. It never takes focus, so the text field where you were typing remains active and the caret stays where you left it. A waveform on the left moves whilst audio is being sent and turns an amber colour whilst the last words are being finalised, so a microphone picking up nothing is visible in the first second rather than afterwards.
Two system permissions
macOS asks for microphone permission before any audio is recorded. Accessibility provides the other half of the feature: watching a modifier key outside the application and pasting into the application with focus. Both are explained where they are requested, and the app keeps showing which one 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 list of recent dictations 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 being built and has not been released. It will require macOS 15 or later and will be distributed from this site rather than the Mac App Store: pasting text into another application is something the App Store sandbox does not permit, and that is the part of Speecho worth having.
Write to support@lulucat.ai to hear when it ships.