You talk.
Your Mac types.

Watch your words appear as you speak. Let go, and they land where your cursor is.

150+ downloads in 18 countries

Free forever  ·  No account  ·  macOS 26  ·  Apple silicon

MailFileEditFormat100%Fri 14:20
New Message
To:Priya Raman
Subject:Friday’s launch timing

Audio never leaves this Mac

From friends who tried it first

It’s so fast. Awesome. Works faster than Wispr.

Aniruth MuraliHas tried Wispr Flow and VoiceInk

I didn’t want to deal with setting up local models. I wanted something simple, sleek and optimized, and now I have it.

HarshineeEarly tester

It’s superb. Everything was nice and clear, from installing to setting up.

Mano RanjitOn an M2 Mac

It’s super nice! Looks very polished.

Syam SundarEarly tester
  • Notarised by AppleChecked by Apple before it opens
  • Your voice stays on your MacNo audio is ever uploaded
  • Free forever, no word limitNo account, no trial
  • 150+ downloadsFrom 18 countries

Two ways

Some things you send.
Some things you read first.

Both start the same way — hold fn and talk. What changes is how you let go, and whether anything reaches the app before you’ve read it.

For the reply you’d have typed in five seconds

#launch

Priya Raman2:34 PM

Numbers for the review are in the doc now.

Dan Whitfield2:37 PM

Nice. I still owe you the churn breakdown — tomorrow morning.

Arun2:41 PM

Can we move the review to Thursday?

Message #launch

Hold fn. Say it. Let go — it’s in Slack before your hand is back on the keyboard.

fnhold

For the draft you want to think out loud and then structure it

Q3 planning

Q3 planning

We shipped the onboarding rewrite last week. Open question is what goes out next, and in what order.

Hold fn, tap space, then let go and keep talking. It waits in the panel until you’ve read it and pressed Return.

fnholdspacetap

Four versions

Press them. This is what they actually do.

Every version is cached after the first run, so flipping back and forth is free — that’s the point of having buttons at all. Try them: these behave the way the real ones do.

Um so before Friday I need to do three things, uh finish the churn breakdown, get the pricing change reviewed, and and write up the onboarding notes, if we don’t do all three we can’t ship.

Insert↩
On this Macnothing ran — your words, untouched

Original always stays. Tidy, Polish and Structure each have a switch in Settings.

Sound on

See it in forty seconds.

A NOTE FROM THE MAKER

Hi, I’m Annamalai. I make Speaklively.

I built it because I spend my days writing — replies, notes, long prompts to AI tools — and talking is simply faster. I wanted it to feel like something Apple forgot to ship: hold a key, say it, let go.

It’s just me. Dictation is free and will stay free, there’s no account to make, and your voice never leaves your Mac.

If something breaks or feels wrong, tell me. Choose Tell the Maker in the menu bar, or write to me here. It comes straight to me.

— Annamalai

That’s the whole gesture. Want it on your Mac?

Download free for Mac

Works where you work

If you can type there,
you can talk there.

Speaklively’s panel opens without stealing focus, so the app you were in stays the app you’re in. When you press Return the text arrives at the caret — no click back, no window to dismiss, nothing to put away.

TerminalShellEditView
arun — -zsh — 80×24

~/speaklively % swift build

[1/2] Compiling SpeaklivelyCore

[2/2] Compiling Speaklively

Build complete! (12.34s)

~/speaklively %

Text goes in the same way ⌘V does, so there’s nothing to set up per app. Password fields too — and when Speaklively can tell it’s a password field, what you say there is never kept in your history.

What stays and what goes

Your voice never leaves this Mac.
Your words leave only when you press.

Private enough for the document you can’t afford to leak, and it still works on a train with no signal. Hearing you runs on Apple’s on-device models, and tidying you up is simple rules on this Mac, so there’s nothing to send in the first place.

Stays on this Mac

Your voice

Never written to disk — not a temp file, not a cache.

The transcription

Apple’s on-device models, running here.

Tidy’s cleanup

Also here — simple rules on this Mac, no model and no network.

Your last 100 dictations

Plain text, on this disk. Switch history off and nothing is written at all.

All of it works with the Wi-Fi off.

Leaves only when you press

The text of one dictation

Only the transcript you pressed Polish or Structure for. Nothing else, and never the recording.

It travels through a relay I run, which counts what the call cost so a beta token can have a ceiling, and keeps nothing else — no transcript, no prompt, no reply. Paste your own Anthropic key in Settings and it skips the relay entirely.

One exception, and it ships off. Vocabulary suggestions are the only feature that sends more than the single transcript you pressed for — they send a slice of your history, so Claude can learn the words you keep having to correct. The switch is in Settings, off, and you can leave it there.

Once a day, it asks whether there’s a newer version. That’s the one thing that goes out without you pressing anything. It carries which build you’re running, a random number made when you installed — so I can tell forty people running it from one person opening it forty times — and how many words you’ve dictated since it last asked. A count, never the words themselves: the number 412, and nothing about what any of them were. It’s the only way to know whether anyone finds this useful, because dictating with Polish off never touches a server at all. Nothing about your Mac, and nothing you dictated. The switch is in Settings under Privacy, and turning it off stops all of it — including the app saying which install it is when it checks for updates. Updates themselves carry on; they are a separate switch now.

No account. No upload. Want a build?

Download free for Mac

Frequently asked questions

Can’t find yours? Ask me.

What is Speaklively?

Speaklively is a free dictation app for Mac. Hold the fn key (or a shortcut you choose), talk, and let go: the words land in whatever you were typing in, and you watch them appear while you’re still speaking. Transcription runs on Apple’s on-device speech models, so it works with no network and your voice never leaves the Mac. It needs macOS 26 on an Apple silicon Mac. Dictation is free with no word limit and no account, and the optional AI cleanups (Polish and Structure) send one transcript to Claude only when you press for them.

Do I have to give you my email to download it?

No. On a Mac the download starts the moment you press the button, with nothing to fill in. The AI cleanups switch on from inside the app, and you never handle a key: the first 15 need no email at all, and verifying your email there with a six-digit code adds 100 more. The page after the download offers to email you the link and those steps, if you want them. That address gets the one email you asked for and nothing else, and it is never sent to website analytics. Verifying an email in the app does start a few emails from me over your first week, about getting started, and replying stop ends them.

What will it cost me later?

The parts that run on your Mac — dictation, live transcription, Tidy, your history — are free forever. Not free for now: free, permanently. They cost me nothing each time you use them, so there is nothing there I could honestly charge for, and a price that appears later on something that was always costless is exactly the move I would be annoyed by. The AI cleanups are the one part that does cost me money, every single press. Your first 15 are free with no email, and 100 more once you verify your email. After that it is $39 for 12 months — though checkout is not open yet, so for now you can point them at your own Anthropic key so nothing of yours comes near me, or switch them off. Everything in the first list carries on exactly as it did.

Is it safe to install?

Yes. Speaklively is notarised by Apple: before a version reaches you, Apple checks it for malware and confirms who signed it. The first time you open it, macOS asks once whether you want to open an app from the internet, and that’s all. It asks for your microphone, speech recognition and permission to type for you, each one explained on screen, and each one something you can switch off in System Settings.

Which Macs won’t run it?

Anything before macOS 26, and every Intel Mac. That’s a narrower requirement than anything else in this category, and it’s also the reason it can transcribe live without the network.

Which languages does it handle?

macOS 26 ships two on-device transcribers and Speaklively uses whichever one covers your language — 54 between them, Hindi included. The Whisper-based tools do 100+, so this is genuinely fewer. If your language isn’t in Apple’s set, this is the wrong app for you today.

What exactly leaves my Mac, and when?

Your voice never does. Transcription and Tidy both run on-device. When you press Polish or Structure, that one transcript goes out — through a relay I run, which counts what the call cost and keeps no transcript, prompt or reply — and on to Claude. Nothing goes anywhere until you press for it — or until the panel opens, if it opens on Polish or Structure.

WHY SPEAKLIVELY

See every word before it lands.

Fast enough to think out loud, careful enough for the email you’d hate to send twice. It runs on your Mac, so it works offline and your voice never leaves the machine.

Watch it hear you

Your words appear while you’re still talking, so you know it got them before anything lands.

Your voice stays put

Speech becomes text on your Mac, using Apple’s on-device models. No audio is uploaded. Ever.

Free, with no word limit

Dictation, live words and Tidy cost nothing, forever. The AI rewrites are an optional extra.

Comparing apps? Speaklively vs Wispr Flow · vs Superwhisper

See your words as you speak  ·  Nothing leaves this Mac  ·  Works offline

Dictation free forever — macOS 26 on Apple silicon.