The fastest way to write on your Mac. Private, on-device dictation & meeting notes. Talk in any language.
Cleanup is opt-in. Turn it on and filler, grammar and spelling are tidied on-device before the text pastes. An AI rewrite for deeper polish is optional too.
curl -fsSL https://charandeepkapoor.com/openwispr/install.sh | sh
Roughly three times faster, before you count the backspacing.
+ anywhere you can type
Fillers stripped, sentences capitalized, your vocabulary corrected. All on-device, before it pastes.
Runs on the Apple Neural Engine via WhisperKit. Your voice never touches a server. Works fully offline, no account, no bill.
A floating pill shows your words as you speak, so you see the transcription before it lands. Release the key and it pastes at the cursor.
A custom dictionary plus corrections it remembers. Product names, teammates, jargon: teach it once and it types them right.
Say "add my email" and your address pastes itself. Same for your LinkedIn, your booking link, your sign-off. Phrases you set once, in the words you actually say them.
Auto-detected or pinned. Speak Hindi and get Roman script, or have it translated to English. Code-switch mid-sentence, it keeps up.
Every dictation saved and searchable. An Insights page shows your pace, words per day and the apps you dictate into. Light and dark themes, plus per-app disable and sound cues where you want quiet.
Saved next to the transcript and shown for past meetings. Runs on Ollama or Apple's on-device model; Hindi and other languages Apple can't read fall back to Ollama.
A bundled Chrome extension names speakers on Google Meet. An experimental on-device screen read finds the active speaker on Meet, Teams and Zoom.
Failed dictations are saved and can be retried. The pill warns if your mic is silent. Double-tap the trigger key to dictate hands-free until the next tap.
An openwispr command transcribes files and searches history and meetings. openwispr:// links start dictation from Shortcuts and scripts. Sparkle keeps the app up to date.
Runs on the Apple Neural Engine via WhisperKit. Your voice never touches a server. Works fully offline, no account, no bill.
A phrase fires. A bare word never does — "send me an email tomorrow" stays exactly as you said it.
Each snippet takes as many phrasings as you need, because "add my linkedin" also comes out "add my linked in". Set your own in the Snippets tab.
OpenWispr captures your mic and the call's system audio, labels who said what, and saves the transcript automatically. No bot joins the call.
Saved to ~/Documents/OpenWispr
I can take the migration if someone reviews the schema today.
I'll review it after lunch. Do we ship Thursday or Friday?
Thursday. The launch email is already drafted.
Works for me. Let's lock it.
Drafts emails and docs at speaking speed, then edits instead of typing from scratch.
Dictates commit messages, PR reviews, and prompts into Cursor without breaking flow.
Lets transcripts and summaries pile up in a folder while actually listening on the call.
Early-bird: 75% off the first 10 buyers with code EARLY10
Then 50% off the next 20 (EARLY20) and 25% off the next 50 (EARLY50).
Why pay for open source? You get the signed build, automatic updates and support for the work. The source is MIT, and you can build it yourself.
Normal people don't want an API key or a monthly bill. OpenWispr cleans your words on your own Mac, for $49, once.
| OpenWispr | Wispr Flow | Muesli | |
|---|---|---|---|
| On-device | ✓ | ✗ cloud | ✓ |
| Price | $49 once (early-bird from $12) | $15/mo Pro* | Free |
| Meetings | ✓ | ✗ | ✓ |
| AI cleanup | On-device*, included | Cloud | Your own API key |
| Cleanup, zero setup | ✓ | ✗ paid cloud | ✗ needs API key |
| Open source | MIT | ✗ | MIT |
| Works offline | ✓ | ✗ | ✓ |
*Cleanup runs on-device, built-in on macOS 26 with Apple Intelligence; on older Macs bring an API key or run Ollama (both optional). Wispr Flow's free tier caps at 2,000 words per week and processes audio in the cloud.
Installs to /Applications and launches. No Gatekeeper dance — the script strips quarantine for you.
curl -fsSL https://charandeepkapoor.com/openwispr/install.sh | sh
A seven-step wizard: mic + live level meter, Accessibility, speech model (~1.5 GB once), press-test your hotkey, then a practice dictation.
Release — clean text lands at your cursor. OpenWispr lives in the menu bar, not the Dock. Rebind the trigger anytime in Settings.