Flagship
Voice editing
Select any text, hold the dictation key, and say “make it more formal” or “fix this”. lisper rewrites it in place.
“make it more formal” replaced in place
The fastest dictation on Mac
Speak. It's already written.
Dictation that lands at your cursor in about a second. Cleaned up, multilingual, native on your Mac.
macOS 13 and later. Apple silicon.
~1s latency Unlimited words Voice stays in the EU Native menu-bar app Multilingual Push-to-talk hotkeys
Speed comparison
Time from releasing the key to text at your cursor. Lower is better.
Measured end to end, warm path.
See it in action.
Reply in your tone, turn rambling into a clean note, or fix any text in place. lisper reads the context and does it, right at your cursor.
ML
Mara Lindqvist
online
Hey, can you send the Q3 numbers before the call?
Notes
15 Jun 2026 · 12:18
Draft
we was gonna send the report tommorow but its not done yet
From rambling to ready.
Filler words gone, self-corrections applied, punctuation and lists handled. You talk, lisper writes it properly.
um so i basically need to send the the email to the team about the launch being pushed to thursday and tell them to prep the demo
I need to send the email to the team about the launch being pushed to Thursday, and tell them to prep the demo.
Three steps. One key.
Hold a hotkey
Left Control for dictation. Push-to-talk, or double-tap for hands-free.
Just talk
Glowing energy waves show lisper is listening. Your music mutes itself.
Text appears
Cleaned up, formatted, at your cursor, in any app. In about a second.
Five things nothing else does.
The reasons people switch and stay.
Translate while you dictate
Say “translate to English” and keep talking. You get idiomatic translation, not a literal word swap.
Vertical profiles
Medicine, law, developer. Each profile loads its own vocabulary, formatting, and tone.
Spoken snippets
Say “sign-off” and your saved text block drops in, word for word.
App-aware tone
Casual in Slack, formal in Mail, terse in Terminal. lisper adapts to where you type.
Dictation, done right.
Not a transcript. Clean, formatted text in your voice, with the filler words gone.
Ten writing styles
Standard Natural Short Casual lowercase Refined Eloquent Business Bullet points Verbatim
- Spoken formatting like “new paragraph” or “bullet list”
- Vocabulary biasing for names and jargon
- Self-corrections applied as you speak
- Silence gate and hallucination filter: no junk when you pause
Actions on whatever you see.
Hold the action key and say what you want. lisper finds the right context and does it.
It finds the text, so you don't have to.
Selection, focused field, browser page, clipboard, then a screenshot with OCR. The context chain tries every source until it has something to work with.
Reply in tone
Say “reply politely” and lisper reads the focused message, then writes the answer in the right tone.
Prompt mode
Dictate a rough idea, get a structured, ready-to-use AI prompt at your cursor.
Summarize
Condense a selection or the whole screen with one spoken command.
Translate
Turn the text in front of you into another language, spoken.
Screenshot to text
No selectable text? lisper grabs a screenshot and reads it with Apple Vision OCR.
Action
Custom commands
Define your own: a trigger phrase, a prompt, and where the result lands.
Nothing gets lost.
Every dictation and action lands in your history. Re-insert or copy any result with one click, a Cmd+L away.
- Re-insert any result at your cursor
- What you said and the result, side by side
- One keystroke to open it
Make it yours.
Ten voice-reactive HUD styles, your color, your size. The orb glows blue for dictation, purple for prompts, red for actions.
Watch your words appear.
Speak and your words show up live, right there. Then the clean text lands at your cursor.
Works everywhere you write.
Text lands at your cursor in any app. No plugins, no integrations to wire up.
Speaks your language.
Dictation, actions, and the whole interface, in many languages, with native recognition.
English Deutsch Français Español 日本語 中文 and more
Your voice never leaves the EU.
GDPR-compliant by default, not as an afterthought. Your audio is processed in the EU, transcribed on the fly, and never stored. Models are locked, your token is bound to your device.
GDPR-compliant by default Voice never leaves the EU Audio is never stored Token bound to your device Locked models, no abuse
Simple pricing.
24 hours free, no credit card. Then keep going for less than a coffee a month.
- Unlimited dictation, no word limit
- GDPR by default, voice stays in the EU
- Voice editing, actions and prompt mode
- All writing styles and vertical profiles
- 10 voice-reactive HUD styles
- Free auto-updates
The free trial starts when you open the app. Subscribe in-app whenever you are ready.
Questions, answered.
Which platforms are supported?
lisper is a native macOS app today (macOS 13 and later, Apple silicon and Intel). More platforms are on the roadmap.
How fast is it really?
About one second from releasing the key to text at your cursor. Faster than Wispr Flow and Sprecho in our tests.
Is there a word limit?
No. Dictate as much as you want, there is no cap and no per-word metering.
What happens to my voice?
Your audio is processed in the EU, GDPR-compliant by default. It is transcribed on the fly and never stored, and your token is bound to your device.
Which languages does it handle?
Dictation and the whole interface work in many languages, with native recognition.