Apps

Whisperpad

Press a key, speak, and the words appear wherever your cursor already is. The speech model runs on your own machine. No audio ever leaves your PC — there is no server to send it to.

Available now Download for Windows, 714 MB

What it does

How it works

  1. Put your cursor wherever you want the text.
  2. Hold the hotkey — Ctrl+Shift+D unless you change it — and speak.
  3. Release. The audio is transcribed on your machine and pasted straight in.

Choosing a model

Models download once, straight from Hugging Face, and are then yours on disk. Bigger is more accurate and slower; a graphics card makes the large ones practical.

Available models
Model Size Best for
base~140 MBAny CPU, older machines. Fast, decent accuracy.
small~460 MBA good balance on modest hardware.
distil‑large‑v3~1.6 GBThe default. Best speed against accuracy without a GPU.
distil‑large‑v2~1.6 GBEnglish only, very fast, excellent for English speech.
medium~1.5 GBNoticeably better than small. Wants a GPU for real‑time use.
large‑v3‑turbo~1.6 GBNear large‑v3 quality at roughly twice the speed.
large‑v3~3.1 GBThe most accurate. Needs a GPU with 4 GB or more of memory.

What you need

Getting it

Whisperpad for Windows

714 MB, hosted on GitHub. Nothing to install, and nothing to sign up for. All releases and release notes.

  1. Extract the zip anywhere you like.
  2. Open the Whisperpad folder and run Whisperpad.exe, keeping the _internal folder beside it.
  3. Windows will warn about an unsigned program. Choose More info, then Run anyway. That warning means the software has not been through paid code signing, not that anything is wrong with it.
  4. Open Models and download one — base to try it quickly, or distil‑large‑v3 for everyday use.
  5. Put your cursor where you want the text, hold Ctrl+Shift+D, and speak.

What Whisperpad stores · Terms of service

Why the download is large

Most of it is the NVIDIA CUDA runtime, so the app can use your graphics card — that is what makes the bigger, more accurate models fast enough to use as you speak. The rest is the Python runtime and the audio libraries.

Everything needed to run is in the zip and nothing else is: no installer, no Python to set up, no separate runtime to hunt down, and no source code — just the compiled program and the libraries it loads.

It works without an NVIDIA card as well, using your processor instead. On those machines stick to base or small. The speech models themselves are downloaded separately from inside the app, so you only fetch the one you actually want.