Skip to content

Whisper Desktop, made simple: speak and get text, instantly.

WhisPaste is a free, open-source desktop app that turns your voice into text anywhere on your computer. Press a hotkey, speak, and the words appear right where your cursor is — no typing, no cloud, no account needed.

What is a "Whisper desktop app"?
It's a desktop application that runs OpenAI's Whisper speech-recognition model directly on your computer — not in a browser tab, not in the cloud. WhisPaste is exactly that: whisper.cpp bundled into a native app for Windows, macOS and Linux.
How does WhisPaste turn Whisper into a desktop tool?
WhisPaste bundles whisper.cpp straight into the app, so there's no Python environment or separate model download to manage. Press a hotkey anywhere on your system, speak, and the transcript is pasted right at your cursor.
Does the Whisper desktop app work offline?
Yes. All transcription happens locally — no cloud connection, no account, and no internet required once the app and model are installed.
Does it run on older or non-NVIDIA GPUs?
Yes. On Windows and Linux WhisPaste accelerates through Vulkan — one path that covers NVIDIA, AMD and Intel cards alike, older models included; on Apple Silicon it uses Metal. Without a usable GPU driver everything runs on the CPU, and if a GPU crashes twice while loading a model, the app permanently switches itself to CPU.
Is WhisPaste free?
Yes. WhisPaste is free and open source under the MIT licence — no account, no subscription, and no paid tier in the desktop download.
Is it safe to use?
The full source code is public on GitHub and can be audited by anyone. Transcription runs locally by default, with no account and no telemetry that carries your audio or text.
Where does the Whisper transcript end up?
Right where your cursor is. WhisPaste runs Whisper as a system-wide voice-input layer, so the transcript lands directly in the editor, chat window, terminal or form field you are already working in — no upload step, no queue, no copying out of a separate transcript window. That is what turns Whisper from a speech-recognition model into an everyday desktop input method.

Technical details

Setup: one installer, no Python environment

WhisPaste embeds whisper.cpp (the C++ port of OpenAI Whisper) directly inside the desktop binary. After install, you pick a model size from a drop-down, the app downloads it once, and from then on transcription runs fully offline on your machine. No virtualenv, no pip, no CUDA toolkit — the GPU acceleration ships inside the download (Vulkan on Windows and Linux, Metal on Apple Silicon).

Performance: CPU works, GPU is five times faster

whisper.cpp runs on plain CPU on every supported machine (Windows 10+, macOS 10.15+, Ubuntu Linux), so an 8 GB laptop without a discrete GPU is enough for the compact model. On a machine with a dedicated GPU (Vulkan on Windows and Linux, Metal on Apple Silicon), the same transcript is produced roughly five times faster. Apple Silicon uses unified memory, so 8 GB already covers the balanced model. No GPU at all? WhisPaste's second on-device engine, Parakeet, is built CPU-first and stays several times faster than Whisper on the same hardware, at the cost of language breadth (about 25 languages instead of 99).

Local vs cloud: same Whisper, different trade-offs

Local Whisper keeps audio on your machine, costs nothing per minute, and works without internet, at the price of a one-time model download and slightly more RAM. Cloud providers like OpenAI or Deepgram trade those resources for raw speed and the largest models. WhisPaste lets you pick per session: stay local by default, switch to a cloud provider when you need maximum speed on a long recording.

  1. Install WhisPaste and pick a Whisper model

    Download WhisPaste from the Microsoft Store or GitHub. On first launch the setup assistant suggests a model size based on your hardware: compact for an 8 GB laptop, balanced for 16 GB with a GPU, premium for higher VRAM.

  2. Let the model download once

    WhisPaste fetches the chosen whisper.cpp model file in the background and verifies it. The download resumes after interrupted connections, so a flaky network does not force you to start over. After that, transcription runs fully offline.

  3. Press your hotkey and speak

    Place the cursor wherever you want the text, hold your configured hotkey, and speak. whisper.cpp transcribes the audio on your machine and the transcript appears at the cursor: no upload, no browser tab, no copy-paste step.