Whisper Freely
Whisper Freely.howprivacydownload
**●** Local dictation for macOS
recording…
Well then you'll love **Whispr Freely**! Just whisper at your computer (you know, like a normal person) and voilà — Ben Horowitz loses a yacht. Everything runs on **your** Mac: no cloud, no account, no audio ever uploaded.
Download for macOSFree · Apple Silicon · macOS 14+
Model whisper-large-v3-turbo
Engine Apple MLX · Metal
Typical turnaround**~2 s**
Languages 99
Network calls while dictating**0**
How it works
One key you already have. Tapped twice.
No window to find, no shortcut to memorize, no palette to summon. Whisper Freely lives in your menu bar and listens for one gesture, system-wide.
1
Double-tap fn
You hear a soft pop ◉ and the menu-bar icon turns red. The mic is live.
2
Say it
Dictate a sentence or a few paragraphs — into any app, any text field, mid-thought.
3
Tap fn once
About two seconds later your words are pasted at your cursor, punctuated and cased.
Privacy
Private by construction, not by policy.
> The only server involved is your Mac.
- audio path Microphone → memory → Apple-silicon GPU → your clipboard. Recordings are never written to disk, and never leave the machine.
- network Zero network calls while dictating. The model is fetched once on first launch (~1.6 GB), after which everything works with Wi-Fi off.
- accounts None. Nothing to sign into means nothing to be logged, profiled, or breached.
- business model There isn't one. Whisper Freely is free — it exists because on-device transcription got good enough that it should be.
What you get
Small app. State-of-the-art ears.
Frontier-grade accuracy
OpenAI's Whisper large-v3-turbo — the same family behind the best cloud dictation — running on your GPU via Apple's MLX framework.
Works in every app
Mail, Slack, your editor, a terminal — if you can type there, you can dictate there.
99 languages
Dictate in English, Urdu, Japanese, or Portuguese and switch mid-day. Language is detected automatically.
Fast on battery
Runs on the efficiency of Apple silicon — a few seconds of GPU per dictation, idle the rest of the time.
Menu-bar quiet
A single 🎙 in your menu bar. Red while recording, back to quiet when done. No dock icon, no windows.
Long-form friendly
Up to three minutes per take — dictate a full email or a memo section in one breath, not phrase by phrase.
Download
Version 1.0 · signed 520 MB app · requires an Apple Silicon Mac on macOS 14 or newer. **The public download link goes live once Apple's notarization clears.**
Download WhisperFreely-1.0.zipnotarization pending
On first launch, macOS will ask for three permissions. Each maps to one thing the app visibly does:
Input Monitoring
To notice the fn double-tap — the app listens for that one gesture and ignores everything else you type.
Microphone
To hear you while the red dot is on. The mic is opened when you start a dictation and closed the moment you stop.
Accessibility
To paste the finished text at your cursor. If you skip this, transcripts still land on your clipboard.
Questions
Fair questions
Does it really work offline? Yes. The model downloads once on first launch. After that you can dictate on a plane with Wi-Fi off — there is nothing to reach and no one to phone.
How accurate is it? Whisper large-v3-turbo sits within a fraction of a word-error-point of the best cloud transcription on standard benchmarks, and it handles accents, jargon, and punctuation gracefully. Short answer: you stop checking its work.
What happens to my recordings? They exist in RAM for the seconds between your two fn taps, get transcribed on the GPU, and are gone. Nothing is saved, uploaded, or retained — there is no code path that could.
Why does my Mac's fan not spin up? A dictation costs a few seconds of GPU time via Apple's MLX framework, similar to exporting a photo. The rest of the time the app is idle, holding the model warm in memory so your next dictation starts instantly.
Intel Macs? Not currently — Whisper Freely is built on MLX, which requires Apple silicon (M1 or later).
Completely free. _Completely yours._