Don't type. Speak —
and it never leaves your Mac.

LocalWispr turns your voice into polished text in every app — email, chat, docs, code. The AI runs on your Mac's Neural Engine. No cloud. No account. No audio upload, ever.

Free to try · Apple Silicon · macOS 14+ · Notarized by Apple

Hey, I'll meet you there at six tonight. Actually, five tonight.
Most people speak 3–4× faster than they type. Hold a key, say it, done.

Everything the cloud apps do. Without the cloud.

Hold Fn, speak, release — clean, punctuated text appears at your cursor, in any app.

⌨️

Works in every app

Mail, Slack, iMessage, Notion, your editor, your terminal. If you can type there, you can speak there.

AI polish, on-device

"Meet at six — actually, five" becomes "Meet at five." Spoken lists become bullet points. Filler words vanish. All on Apple Intelligence, all local — and a safety check guarantees it never changes what you meant.

👁️

See it as you speak

A live waveform and rolling transcript show exactly what's being heard — and a crossed-out reveal shows every edit the AI made.

🙌

Hands-free mode

Double-tap the hotkey to lock recording — dictate a whole email leaning back in your chair, tap once to finish.

📖

Your words, your way

A personal dictionary teaches it your names and jargon ("k eight s" → "k8s"). Snippets expand "my work address" into the whole thing.

🌍

25 languages

Dictate in English, Spanish, French, German, Portuguese, Italian, Dutch, Polish, Ukrainian and more — automatically detected.

Neural Engine fast

Transcription runs ~190× realtime on Apple Silicon. Your words land before cloud apps would finish uploading the audio.

🔌

Works in Airplane Mode

One model download at setup (~1 GB), then the internet is optional. Forever. Try it with Wi-Fi off — nothing changes.

Private by architecture, not by promise.

Cloud dictation apps stream your voice — and often the text on your screen — to their servers, then share transcripts with third-party AI providers. LocalWispr was built so that's impossible: there is no server.

LocalWisprCloud dictation apps
Your voice uploadedNever — processed on your MacEvery dictation, streamed live
Reads your screenNeverOften — window text sent as "context"
Works offlineYes, completelyNo — outages stop your dictation
Account requiredNoneYes
Analytics & telemetryZero — no tracking code existsExtensive
Your transcripts liveIn plain files on your MacOn their infrastructure
PriceOne payment, yours forever$12–15 every month

One price. No subscription. It's your computer.

Download free and evaluate as long as you like — the app is fully functional. If it earns a place in your day, buy a license.

$19 once
  • Lifetime license, all your Macs
  • Free updates, delivered securely in-app
  • Offline license activation — even buying respects your privacy
  • Support from an actual human
Buy a License

Checkout page coming soon — for now, email and a human sends your key.

Questions

Is it really 100% offline?

After a one-time speech-model download (~1 GB from Hugging Face at setup), yes — every transcription, every AI edit, every feature runs on your Mac's Neural Engine. Block the app's network access or turn on Airplane Mode: nothing changes. That download is the only network request the app ever makes, besides checking for updates when you ask it to.

What Macs does it run on?

Any Apple Silicon Mac (M1 or newer) on macOS 14 Sonoma or later. The optional AI polish feature uses Apple Intelligence, which requires macOS 26.

How accurate is it?

LocalWispr uses NVIDIA's Parakeet speech model, which outperforms Whisper large-v3 on public English benchmarks — with punctuation and capitalization built in. A personal dictionary handles your names and jargon.

Why do you need Input Monitoring and Accessibility permissions?

Input Monitoring lets the app notice the hotkey being held in any app — it's a listen-only tap that architecturally cannot log or alter your typing. Accessibility lets it type the transcript at your cursor. The app's Settings shows a live diagnostic of both.

What happens to my recordings?

Audio is transcribed in memory and discarded. Transcripts are saved to a local history file only if you keep that setting on — you can search, export, or delete it anytime. Nothing is retained anywhere else, because there is nowhere else.

Refunds?

The evaluation is free and unlimited, so you'll know before you pay. If you buy and regret it anyway, email within 30 days and you'll get your money back.