On-device, on Apple Silicon. Your voice never leaves your Mac.
Four pipeline steps. Zero audio uploaded. About two seconds from voice to paste.
Press your hotkey and talk naturally. No need to slow down or speak formally. Just say what you mean.
AI on your Mac converts speech to text instantly. Everything runs locally. Your voice never leaves your device.
Grammar is fixed, filler words are removed, and your meaning is preserved automatically.
Clean, polished text appears wherever you're typing, in any app, any field, without switching windows.
Everything happens in parallel
Recording, transcription, and polishing overlap. That's how EnviousWispr delivers results so fast.
Built to be fast and private
Choose how your text gets cleaned up
Turn cleanup on and pick your engine. Each one is good at something different, and every option except a cloud key runs on your Mac.
Apple's built-in AI
On the latest macOS, cleanup runs on-device with nothing extra to download. The zero-setup way to get started.
EG-1, our own model
We tuned it just for dictation cleanup: it turns a spoken list into a real list, breaks a wall of talk into clean paragraphs, and keeps only the corrected version when you fix yourself mid-sentence. Runs fully on your Mac.
Your own local model
Run any local model through Ollama, fully offline, if you would rather bring your own.
Your OpenAI or Gemini key
Prefer a cloud model? Add your own key. Only your text is sent, never audio, and we ask the provider not to keep it.
How EG-1 compares on cleanup quality
Share of 1,890 real dictation cases each model cleaned up correctly, scored on the same cases by the same judge.
Our own benchmark, not an independent review. The eval harness and prompts are public; the test cases are personal dictations and stay private.
Everything you need, nothing you don't
Powered by WhisperKit and Parakeet, transcription runs entirely on your Mac. No audio ever leaves your device.
Filler words removed, grammar corrected, your meaning preserved. Runs on-device with EG-1 or Apple Intelligence, or with your own OpenAI or Gemini key.
Automatically detects when you start and stop speaking, so you never have to babysit the recording process.
Polished text pastes into any macOS application: email, Slack, Notes, browser forms, terminals. Everything.
Hold your hotkey to record, or double-press to lock into hands-free mode for longer dictation sessions.
Use on-device polish with EG-1 (our own model), Apple Intelligence, or Ollama, or bring your own OpenAI or Gemini key. Cloud polish requests include store: false so providers are asked not to retain the text.
Teach the app to recognize names, acronyms, and domain-specific terms that general models consistently get wrong.
Built in Swift for macOS 14 and up. Lives in your menu bar, uses minimal resources, feels at home on your Mac.
Recording, transcription, and AI polishing run in parallel. The result arrives almost the moment you stop speaking.
Ready to try it?
Free to download. No account. Local by default. No catch.