Speak.
It types.
Nothing leaves your Mac.

Yes. Every feature — dictation, all the languages, file transcription, AI polish, history, profiles — is free, with no trial timer, no watermark, and no locked settings. There's no account and nothing to buy.

All three turn speech into text on macOS. Whisperer is completely free — every feature, no subscription — and runs entirely on-device, so nothing is sent to a server. Superwhisper also works on-device, but its larger models and some features need a paid plan. Wispr Flow processes your speech in the cloud and, beyond a small weekly free allowance, is a paid subscription. If you want free, fully local dictation with no account, that's exactly what Whisperer is.

Nowhere. Audio is captured, recognized on your Mac's Neural Engine, and turned into text entirely on-device. Whisperer makes no network calls while you dictate; the only network use in the whole app is downloading the speech models, once.

Yes. After a one-time download of the speech model, dictation runs entirely on your Mac and works with no connection at all — even in airplane mode. The only time Whisperer uses the network is that first model download; there's no account to sign in to and nothing to sync.

Anywhere you can place a text cursor: native Mac apps, browsers, Electron apps like VS Code and Slack, terminals. The finished text is inserted with one reliable paste — and if an app refuses it, the text is on your clipboard, guaranteed. Password fields are detected and left strictly alone.

The English model is the fastest way to dictate in English. The multilingual model covers a wide range of languages, including Arabic, Spanish, French, German, Chinese, Japanese, Korean and Hindi, and it can auto-detect the language you're speaking. The app's interface is localized into 10 languages, including full right-to-left Arabic.

Whisperer runs NVIDIA's Nemotron/Parakeet-class streaming models via Apple's Neural Engine, showing partial words while you're still speaking. A latency–accuracy slider lets you pick snappier responses or a more careful transcription; file transcription runs at many times real-time.

An optional pass by a small language model that runs locally: it removes fillers, fixes self-corrections ("on Friday— no wait, Monday" becomes "on Monday"), and tidies punctuation. It's off by default, English-only, requires an explicit ~1 GB model download, and never sends anything anywhere.

macOS 14 (Sonoma) or newer on Apple Silicon (M1 and up) — on macOS 26 you get the full Liquid Glass look, and earlier systems get a clean native fallback. The app itself is about 31 MB; the speech model you choose downloads once on first run (about 250 MB for English, about 1 GB for multilingual). It asks for Microphone and Accessibility permissions — the second is how it types into other apps.

Whisperer checks this site for new versions and offers to install them in one click — every update is signed and Apple-notarized, and the updater verifies the signature before installing. You can turn automatic checks off in Settings → General, or check manually any time.

The App Store sandbox forbids exactly the two things that make Whisperer useful: a system-wide hotkey and typing into other apps. So it ships the classic Mac way — a signed, Apple-notarized download that Gatekeeper opens without a warning.