Private · On-device · Apple Neural Engine
Videos, calls, podcasts: transcribed as they play and drawn as an always-on-top overlay. Nothing is uploaded, nothing is recorded, nothing is written to disk.
Launch week: $5 instead of $9 until 22 August · 14-day refund
14-day refund, no questions asked
One-time $9, every future update included ·
macOS 14.2 or later · Apple Silicon
Unlimited captions, for as long as you like. No minutes to buy, no
account, no subscription.
Switch apps and the captions stay: the overlay is above every window, and lets clicks through.
Click a window to bring it forward. Hold ⇧ and drag the captions to move them, as you would in the app.
Point at the captions and they dissolve under you. Hold ⌥ to stack the last few back up. Both work here exactly as they do in the app.
Subtitles captions any audio your Mac can play, because it taps the app itself rather than integrating with any one service. Whether you are deaf or hard of hearing, listening in a second language, or just working somewhere loud, three situations come up again and again.
01
Zoom, Google Meet, Teams, a Slack huddle, a call in a browser tab: all of it is just audio coming out of an app, so all of it gets captioned. Second language or not, it earns its place the moment an accent is unfamiliar, someone's microphone is bad, or two people talk over each other: reading a word you only half-heard is faster than asking for it again, and it doesn't interrupt anyone.
02
Audio doesn't wait. The moment you switch to your notes, your editor or a browser window, you start losing the conversation. The overlay is always on top of every window and click-through, so it stays where it is while you work in front of it. You can take notes, look something up, and still follow what's being said. A notepad like Granola writes the meeting up afterwards; this is the half that has to happen while it is still going on.
03
A video with no captions, or with automatic ones that are worse than none. A podcast in a language you're still learning. A recorded or a streaming lecture, an interview, a film with quiet dialogue. Captions appear over whichever window is playing it, at whatever text size you set, in nine languages with the language detected for you.
All three have the same thing in common: a meeting, a call and a private recording are none of a server's business. None of this audio is uploaded, because none of it has to be: the model runs on your Mac.
Live audio can't be paused, can't be re-run, and shouldn't have to leave your machine. Everything here follows from that.
It runs locally and offline: no network calls, no accounts, no telemetry. Audio goes from the tap straight into the recogniser and is discarded. The only thing ever downloaded is the model itself, once.
Roughly 0.15 real-time factor: six seconds of speech transcribed per second of compute. The same model on the CPU measured about 100× too slow to keep up with a live stream.
Pick a source from the menu bar and it captures that app and every helper process it spawns, which is what makes it work for browsers and Electron apps, where audio never comes from the main process.
A voice detector runs ahead of the recogniser so backing tracks never reach it. Without it, music fills the model's context and the first words after it are lost.
Optionally start a fresh subtitle when someone else starts talking, the same way a pause does. Off by default: it runs a second model alongside the first.
The default model detects the language itself. English gets seven dedicated checkpoints on top, trading latency against accuracy from 160 ms upward.
Something on top of every window only works if it never becomes the thing you are working around. It takes no clicks, it dissolves where you point, and it gives you back the line you looked away from.
Move the pointer near the box and it fades away underneath it, so the sentence you are reading never covers the sentence you are writing. How much of it goes and how wide the hole reaches are both yours to set. Hold ⇧ to keep it solid.
The box pages like broadcast subtitles: it fills, clears and starts again, so a line you glanced away from is gone. Hold ⌥ and the last finished boxes stack back up above the live one, up to thirty of them, scrollable for the older ones. Let go and they are gone again. Nothing is written anywhere.
⌘, from the menu opens settings: how many lines a box fills before it clears, how solid it is, how far the pointer reveal reaches, how far back ⌥ goes. Every slider applies to the overlay as you drag it, so you set these by watching them rather than by picking a number.
A realtime audio thread that only ever copies, a portable core that never transcribes, and a model running where it belongs.
48 kHz stereo, a callback every 10.7 ms. The realtime thread copies into a lock-free ring buffer and does nothing else.
Down to 16 kHz mono on a worker thread, silence skipped, with about a second replayed ahead of speech so no word starts cold.
A streaming model, not a 30-second-window one: the difference between captions that track the audio and captions that arrive seconds late.
Three-line pages that clear and restart the way broadcast subtitles do, fading four seconds after the last new text rather than after the audio stops.
Everything from the ring buffer to the model boundary is portable Rust that deliberately doesn't transcribe: it hands out frames. The tap and the overlay are the only Mac-specific parts.
14-day refund, no questions asked.
The reason you can point this at a work call is that it is not a service. There is no server, no account and no transcript, so there is nothing to send and nobody else in the loop. The source is published, so none of it has to be taken on trust.
Language is the first thing that rules a model in or out, so it's the top level of the menu. Switching within a pack is instant; crossing between packs fetches the other one and keeps whatever you already have.
Change your mind mid-download and it cancels and starts the new one straight away. Switch back later and it resumes instead of starting over.
No Dock icon, no window to manage. The icon tells you what it's doing: indigo while listening, blue while a model downloads, yellow if the pipeline starts falling behind, and never red, because red means recording, and nothing is ever written anywhere. The switches live in the menu, and ⌘, there opens a settings window for the dials behind them.
macOS has captions built in, free, on every Apple silicon Mac, under System Settings, Accessibility, Live Captions. If that covers what you need, use it. These are the places it stopped covering mine, and there is a row-by-row comparison if you want the long version.
Launch week: $5 instead of $9 until 22 August · 14-day refund
14-day refund, no questions asked
One-time $9, every future update included ·
macOS 14.2 or later · Apple Silicon
Unlimited live captions, for as long as you own the Mac. No minutes to
buy, no account, no subscription.