Voice typing in every Windows app.
Hold a shortcut and speak. A live transcript pill shows every word; let go, and your words land wherever your cursor is: Outlook, Teams, Word, your browser, your code editor. No installer wizard, no admin prompt.
Fast, faithful, and out of your way.
A small app in the notification area that turns your voice into text in whatever you are working on.
Any app, any text field
VoiceInput types where your cursor is, in every Windows app. It never types into a password field.
Hold to talk, or go hands-free
Hold Ctrl+Shift+Space while you speak, or press Alt+Space to talk hands-free and press it again, or any key, to finish.
Your first words, never clipped
The mic opens the instant you press the shortcut and stays ready for 45 seconds, so the next dictation starts instantly. You can turn this off in Settings.
A live pill that never steals focus
A floating transcript shows every word and a live mic level. Move it, resize it or hide it.
Your vocabulary, your spelling
Sign in and your custom vocabulary and settings sync with your other devices.
Clean-up, one switch at a time
User prompt, obvious grammar, custom vocabulary and tone are separate, visible switches. Clean-up tidies what you said and never answers it.
Tones, including code
Formal, Casual, Coding or your own. Press Alt+J and describe the code you want: you get real Java, pasted with its line breaks.
Knows what is on screen
What is on screen goes with a dictation to the clean-up model, so names and terms match. On by default, never from a password field, and you can switch it off.
Never loses a word
Every transcript is copied to your clipboard and saved to your dictation history.
Silent, and never presses Enter
No chimes or spoken alerts, ever. Line breaks become spaces, so a chat message is never sent halfway.
No admin, no wizard
The download installs itself for your user account and starts with Windows. No administrator prompt.
Updates itself quietly
New versions install in the background without a dialog and never interrupt a dictation.
Capture it with one shortcut.
Windows gets the same capture shortcuts as the Mac: record a meeting, grab a screenshot, or hear a page read back, and turn it into a task. Sign in with Google or email to use them. Tasks go to your account's to-do list, the same list the To-Do List app shows; Ctrl+Alt+T shows today's.
- Recordings and live meeting notes with speakers labelled
- A screenshot of the screen or a region, turned into a task
- Read the selected text aloud, or add it as a task
Every shortcut, at a glance.
These are the defaults. Change any of them in Settings.
| Shortcut | What it does |
|---|---|
| Ctrl+Shift+Space | Hold to talk; let go to type it in |
| Alt+Space | Hands-free: press to start, press again (or any key) to finish |
| Alt+J | Java code: describe or dictate code and get real Java |
| Ctrl+Alt+T | Show today's tasks |
| Alt+Shift+1 | Record audio, speakers labelled |
| Alt+Shift+7 | Record a single speaker |
| Alt+Shift+2 | Live meeting notes |
| Alt+Shift+3 Alt+Shift+4 | Screenshot of the screen, or of a region, as a task |
| Alt+Shift+5 | Read the selected text aloud |
| Alt+Shift+6 | Add the selected text as a task |
Installed in one double-click.
- Download and run itIf your browser says the file isn't commonly downloaded, open its downloads list and choose Keep. Then open VoiceInput-Setup.exe. It installs itself for your account, with no administrator prompt, and starts with Windows.
- If Windows asksVoiceInput is not code-signed yet, so SmartScreen may say “Windows protected your PC”. Choose More info, then Run anyway.
- Find the mic and talkA microphone appears in the notification area (click the ^ arrow if it is hidden). Hold Ctrl+Shift+Space and speak.
Windows questions, answered.
Is VoiceInput for Windows free?
Yes. It is a free download, with no subscription, and it includes the clean-up switches.
Why does SmartScreen warn me?
SmartScreen warns about apps that are not yet code-signed or widely downloaded. VoiceInput is not code-signed yet. Choose More info, then Run anyway to install it.
Do I need administrator rights?
No. VoiceInput installs into your own user folder and registers itself to start when you sign in to Windows. Nothing is installed for other users.
Do I need an account?
Not for dictation. Recordings, meeting notes, screenshots and tasks need you to sign in with Google or email, which also syncs your custom vocabulary and settings across your devices.
Does it type while I am still talking?
No. The live pill shows your words as you speak; nothing goes into your app until you finish, and then it all goes in at once. The full transcript is also copied to your clipboard.
How do I uninstall it?
Open Settings from the microphone in the notification area and choose Uninstall VoiceInput. It removes the app and its start-with-Windows entry.
Where do my voice and text go?
While you dictate, your voice is streamed to the speech engine picked in Settings (ElevenLabs by default), which sends back the text; VoiceInput keeps no audio from dictation. With a clean-up step on, the text and the screen context go to the clean-up model (Qwen on Cerebras by default). Pick Built-in dictation in Settings to use the Windows speech recognizer. After a dictation the microphone stays ready for up to 45 seconds; only the last second or so is held, in memory, and it is never saved or sent unless you start another dictation in that time (turn off Keep microphone ready to close it right away). The details, and every provider, are in the VoiceInput privacy policy.
