⌥
Hold
Press and hold the right ⌥ Option key. A small pill slides up from the bottom of your screen — Lispr is listening.
● Early access · macOS
Stop typing. Just hold a key and talk.
Lispr turns your voice into text wherever your cursor is — in any app on your Mac. Hold the right ⌥ key, speak, let go. The words are already there.
Free during early access · macOS 14+ · Apple Silicon & Intel
~200msto transcribe a short phrase
1gesture — hold, speak, release
0windows, clicks or settings
∞apps — if you can type, you can talk
How it works
One gesture. That's the whole thing.
Speak
Say what you mean — in English or Russian. The waveform moves with your voice, so you know it hears you.
Release
Let go of the key. A heartbeat later your words appear exactly where your cursor was — already typed.
Features
Small, fast, and out of your way.
Blazing fast
Powered by Groq Whisper on a global edge network. A short phrase comes back in about a fifth of a second — no waiting, no spinner fatigue.
Works in every app
Notes, Slack, Safari, your code editor, that one stubborn login form. If a cursor blinks there, Lispr can type there.
Speaks your language
English and Russian, detected automatically. Switch tongues mid-sentence — Lispr keeps up without a single setting.
No window, no settings
Lispr lives quietly in your menu bar. There's nothing to configure, nothing to log into, and nothing to learn.
Your clipboard stays yours
Lispr inserts your text and quietly puts back whatever you had copied before. You'll never even notice it borrowed it.
Push to talk
Hold to record, release to send — like a walkie-talkie. No wake word, no awkward always-listening mode, no surprises.
The math
You think faster than you type.
A good typist does about 40 words a minute. Speaking, you cruise past 150 — without thinking about it. Lispr hands those minutes back.
Compare
Where Lispr fits.
Plenty of great dictation tools exist. Lispr makes one trade on purpose: do the single most common thing — talk, get text — with zero friction.
| Lispr | Wispr Flow | Apple Dictation | |
|---|---|---|---|
| Price | Free | $15/mo | Free |
| Subscription | None | Required | None |
| Setup | 3 permissions, done | Account + onboarding | Built in |
| Trigger | Hold one key | Hold / double-tap | Double-tap fn |
| Inserts at your cursor | ✓ | ✓ | ✓ |
| Footprint | Menu bar, ~4 MB | Full app + account | System feature |
| Auto language detect | ✓ | ✓ | — |
Comparison reflects publicly listed details as of May 2026. Lispr is in early access — it does one job, and aims to do it instantly.
Questions
The honest answers.
Is my voice recorded or stored anywhere?
No. Your audio is sent — over an encrypted edge proxy — to Groq's Whisper API purely to be transcribed, then discarded. Nothing is saved on a server, nothing is kept, nothing trains a model.
What permissions does Lispr need?
Three, granted once in System Settings → Privacy & Security: Microphone (to hear you), Accessibility (to paste text into other apps), and Input Monitoring (to catch the ⌥ key). Lispr asks for nothing else.
Which Macs are supported?
macOS 14 Sonoma or newer, on both Apple Silicon and Intel. The whole app is around 4 MB.
Does it work offline?
No — transcription runs in the cloud, which is exactly why it's this fast and accurate. The round trip is about 200 ms, hidden behind the moment you're still speaking.
Which languages does it understand?
English and Russian today, detected automatically — you can even switch within one sentence. More languages are on the way.
Is it really free?
Yes — Lispr is free while it's in early access. If that ever changes, anyone who downloaded it early will be the first to know.
Your next sentence — just say it.
Download Lispr, grant three permissions, and never reach for the keyboard to write a message again.
Download for macOSFree during early access · macOS 14+ · Apple Silicon & Intel