On-device
<0.5s on your GPU
No upload. No queue. No waiting on someone else’s servers.
v1.3.0 · free · local · open source · Mac
Don’t type. Just speak.
On-device dictation in <0.5s — not a ~$2B cloud bill at ~2–3s. Your Mac. Your voice. $0 forever.
v1.3.0
Parakeet Redux
macOS 14+
Apple Silicon
Windows
Live race
Who finishes first?
<0.5s local vs ~2–3s cloud
Listening…
MacWispr
<0.5s
—
Ready
Wispr Flow
~2–3s
—
Ready
Versus
Open source vs a $2B cloud app
Same job. Better defaults. No monthly tax.
MacWispr
- <0.5s local
- Your Mac
- $0 forever
- Mac only
- MIT open source
Wispr Flow
- ~2–3s cloud
- Their servers
- ~$12–15/mo
- Cross-platform
- Closed · ~$2B story
Benefits
Faster. Private. Free.
Less cloud tax. More Mac. One job done well.
Option Space
Hold. Speak. Release. Text lands where you are.
Option+Space
$0
Forever free. MIT. No trial cliff.
Mac only. Windows can wait outside.
Built for Apple Silicon. If you need a power brick to open Chrome, this isn’t for you. Yet.
macOS 14+
Apple Silicon
Windows
Stays on the machine
No account. Audio doesn’t leave your Mac for local ASR. Telemetry is opt-in, anonymous, and never sees your words — read the contract.
Updates itself
Check for Updates… built in (Sparkle). No re-downloading DMGs like it’s 2009.
The math
Even at 80 wpm, your fingers lose.
Keyboard
80 wpm
pretty fast
Mouth
150 wpm
done
Setup · v1.3.0
Install on Mac (Apple Silicon)
v1.3.0: one on-device model (Parakeet Redux), nothing to configure. Signed and notarized by Apple — it opens like any other app.
-
01
Download & install
MacWispr 1.3.0 (DMG) → drag MacWispr into Applications.
-
02
Open it
Open MacWispr from Applications. The first launch sets up the speech model (a one-time download, about a minute on a good connection).
-
03
Mic + Accessibility · dictate
Allow Microphone and Accessibility, then hold Option Space, speak, and let go.
Speak free. Own the default.
Open-source dictation for Mac. No account. No $2B subscription story. Windows can wait outside.