100% local · your voice never leaves this machine

Hold a key. Say the thing. Cleaned-up text lands at your cursor in any app — transcribed, polished, and typed entirely on your machine. No cloud. No subscription. No excuses.

SPEAKR · LIVE
Your dictation shows up here…
hold SPACE to feel it

Unzip, then: run.bat on Windows  ·  bash package_mac.sh on Mac. First run downloads the model — that's the only network call it ever makes.

0bytes to the cloud
$0forever · open source
0.2sspeech → text on GPU

Hold. Speak. Done.

Right Ctrl on Windows, fn on Mac. Release the key and clean text appears at your cursor — fillers stripped, self-corrections applied, lists formatted.

Zero cloud. Period.

Whisper transcription and LLM polish run entirely on-device. The only network call, ever, is the one-time model download. Audit the code — it's all there.

It learns you.

Your names, your jargon, your CamelCase — Speakr picks up recurring vocabulary and spells it right, getting sharper the more you talk. Locally, obviously.