No subscription. No account.
No word limit.
Hears
Fillers, repeats, and take-backs are removed.
Every state in one small capsule. Click it.
Fillers and take-backs go.
Pick the keys for every action.
A local model rewrites the text for where it goes.
Select text, hold Right Option + Right Shift, and speak.
Search, play, and export what you said.
Names and terms, spelled your way.
Drop audio. It waits in a queue.
Text, in a voice you pick.
Heart with 30% Adam
Names, places, and terms come out the way you write them. Use your own list, or a word pack.
Say the change, and a model on your computer rewrites the selected text in place.
Speech turns into text on your computer. It keeps typing with Wi-Fi off.
Choose a voice, mix two, or clone your own. It reads text from any app.
No subscription, no account, no word limit. The code is AGPL-3.0, so you can read it and change it.
Parakeet hears 25 European languages. Whisper adds Hindi and more. S1-mini tidies the text.
Audio and text never leave it, unless you pick an endpoint.
Hushpen sends no usage data. Update checks are opt-in.
Models download only when you ask, and every hash is checked.
AGPL-3.0 licensed. Signed and notarized on macOS.
X11 desktops, x64 and arm64.
AppImage
chmod +x Hushpen-2.3.3-linux-x64.AppImage && ./Hushpen-2.3.3-linux-x64.AppImageUbuntu and Debian
sudo apt install ./Hushpen-2.3.3-linux-x64.debAnswers on privacy, languages, and memory. Not here? Open an issue on GitHub.
Open source, and it runs on your own computer.