Tynda.
Early alpha · free to use · open source

Hold fn. Speak.
It types.

Tynda is a small Mac app that lets you talk instead of typing. Your voice becomes text on your own Mac and is typed wherever your cursor is.

fn — stop · esc — cancel
MESSAGE
fnHold fn and talk

Three gestures, nothing to learn

A small black island appears at the top of the screen while Tynda listens, with a live waveform of your voice. It never takes focus away from what you are typing in.

fn held

Hold to talk

Hold fn, say the sentence, let go. About a second later the text is where your cursor was — a chat, an email, a terminal, a search box.

fnfn

Double-tap for hands-free

Tap fn twice and take your hand away. Talk for a minute or ten. Press fn once more and the whole thing is typed.

esc

Changed your mind

Esc throws it away and nothing is typed. If the text landed in the wrong place, the last phrase is still one click away in the menu.

Nothing is saved. Nothing leaves your Mac.

Your voice is recognised on your Mac by Whisper large-v3-turbo running through Apple's MLX. Once the model is downloaded, Tynda works with the network cable pulled out.

  • No account. Nothing to sign up for.
  • No server. There is no Tynda cloud for audio to go to.
  • No telemetry. The only log is a text file on your disk.
  • No history. The audio is deleted the moment it becomes text, and the text goes only into the app you are typing in.

Will it run on your Mac?

Tynda is not for every computer. Check this before you spend time on the install.

MacApple silicon — M1 or newer. Intel Macs are not supported: the speech model does not run on them.
macOS14 Sonoma or newer.
Memory8 GB minimum, 16 GB recommended. The model stays loaded and takes about 2 GB.
DiskAbout 3 GB for the model and its Python packages.
KeyboardThe fn / 🌐 key set to "Do Nothing" in System Settings → Keyboard.
Not yetWindows, Linux, iPhone.

Install

There is no signed download yet, so Tynda is installed from source. You need the Xcode Command Line Tools. The script does the rest, then a setup window walks you through the permissions and your first dictation.

git clone https://github.com/Markerloop-Team/tynda.git
cd tynda
./install.sh     # checks your Mac, gets the model, builds, opens Tynda
MicrophonemacOS asks once. Click Allow.
AccessibilitySo Tynda can notice the fn key and type the text for you.
The fn keyHas to be free: "Do Nothing" in Keyboard settings. The setup window checks it.

What "early alpha" means here

Tynda was built in a day and has been used on one Mac. It works for its author every day; it has not met yours yet.

It is not signed with an Apple Developer ID, so macOS asks for the permissions again after every update. The hotkey is fixed to fn.

If it breaks, open an issue and attach ~/Library/Logs/Tynda.log.