Whatever it is playing in
Panopto, Echo360, Zoom, a Canvas embed, a YouTube recording, a browser tab. It captures the audio an app produces, plus the helper processes browsers spawn, so the platform is not a compatibility question.
Subtitles · Live captions for lectures
Live captions for lectures,
when you cannot ask for a repeat.
A streamed lecture does not wait, and there is nobody to ask for a repeat. Subtitles captions whatever your Mac is playing, as it plays, on an overlay that sits above the notes you are typing into.
Until 31 October: $9 instead of $19 · 14-day refund
- Free for 7 days, no card, no account
- $19 once, every update included
- 14-day refund, no questions asked
- Download for macOS 14.2 or later, Apple silicon
- Rated 5.0 on Gumroad
The key idea is that the gradient points in the direction of steepest ascent.
Which is why we subtract it, and why the step size matters so much.
Too large and you overshoot the minimum; too small and you never arrive.
Next week we look at how momentum fixes exactly that.
The term you missed is on screen above your notes, in the lecture's own words, and it stays there while you write it down.
Hold ⇧ and drag the captions to move them, as you would in the app.
Hold ⌥ to rewind, and the last few boxes stack back up.
Click in the menu bar: items marked Try all work in this demo.
What it captions in a lecture
A second language, at speed
Sixteen languages with the language detected for you, and reading a word you only half-heard is faster than reconstructing it from context three sentences later.
What your Mac plays, or the room
It taps audio coming out of an app, and the microphone stays closed until you choose it in Listen To. That is the boundary worth knowing: a lecture you stream or play back is the easy case, and a hall you are sitting in works from the microphone, as well as the microphone can hear the lecturer.
Missed terms compound
A conversation tolerates a lost word. A lecture does not, because the definition you missed at ten past is what the next twenty minutes are built on. By the time you notice, the thing you needed is four slides back and nobody is going to return to it for you.
It is worse because you are also typing. Notes and listening compete for the same attention, and the moment you look down to finish a sentence is reliably the moment something important is said. The overlay stays above your notes window and takes no clicks, so the last line said is on screen while you are still writing down the one before it.
And if the lecture is not in your first language, all of that happens at the speed of somebody else's accent.
14-day refund, no questions asked.
Why not the platform's captions?
University video platforms do caption. Panopto generates them automatically in more than twenty languages, and Echo360 transcribes published captures and applies them as captions when its confidence is high enough. Where that is switched on and working, use it. Three things it does not cover.
- Those captions are for the recording. They arrive once the capture has been processed and published. The lecture streaming into your Mac right now does not have them yet, and now is when you need to read it.
- Your institution decides, and you cannot. Whether captions exist at all comes down to a setting somebody else configured and a confidence threshold somebody else chose. There is no toggle for it in your seat. This asks nobody's permission because it never leaves your Mac.
- Nothing leaves your Mac, and nothing stays on it unless you ask. The lecture is never recorded and nothing is sent anywhere to be transcribed; the only thing ever written to disk is a transcript you choose to save. That matters more than usual here: a lecture is somebody else's material.
- Half of a degree is not in the lecture platform. A seminar in Zoom, a talk on YouTube, a recorded conference, a study group huddle, a video embedded in Canvas. One app covers all of them, because it captions your Mac rather than a service.
- You are taking notes, not watching. The lecture plays in one window while you write in another, which is most of the reason to watch a recording at all. Captions inside the platform's player are behind your notes the second you start making them. These stay on top of whatever you are typing into.
Pick a slower model than you would for a call
The English models trade latency against accuracy, and a lecture wants the opposite end of that dial from a conversation. In a call you want the 160 ms model because you are about to reply and a late caption is a useless one. In a lecture you are not replying to anybody, so the extra second costs you nothing and buys accuracy.
Nemotron at 1120 or 2240 ms is the one to use here. It punctuates and capitalizes as it goes, which matters a great deal when you are reading a definition rather than a sentence someone just said to you. Switch it in the menu bar, per lecture if you like.
Lecture questions
- Does it work with Panopto, Echo360, Canvas and YouTube?
- All of them. It captures the audio an app produces rather than integrating with a platform, so a lecture in Panopto, an Echo360 capture, a Zoom seminar, a YouTube recording and a video embedded in Canvas are all the same thing to it: sound coming out of your Mac.
- Will it get the technical terms right?
- Often not, and no speech recognizer will. Universities say as much in their own guidance about automatic captions: accented speech and specialist vocabulary are where accuracy drops. This helps with the sentence you half-heard, not with a term the model has never seen. Expect to correct names, notation and jargon yourself.
- Can I keep the captions to revise from?
- Yes, as a plain transcript: when the lecture stops, the app offers to save it as text, Markdown or SRT, and nothing is written to disk otherwise. For revision, your institution's recording and its transcript are still the better tool when there is one, and usually included in your fees.
- What if my university has not enabled captions?
- Then this works anyway, because it never asks your university anything. Whether platform captions exist depends on an institutional setting and a confidence threshold, and neither is something you can change from your seat.
- Does it work in a lecture hall?
- Yes, through the microphone. By default it captions audio your Mac is playing, which is the lecture you stream, join or play back. For the one in front of you, choose the microphone in Listen To and it captions the room instead; macOS asks for the microphone the first time you choose it. How well it does depends on how much of the lecturer reaches your seat: a laptop microphone at the back of a hall is a harder job than a stream.
- Which model should I use for a lecture?
- One of the slower ones. In conversation you want the 160 ms model because you are about to reply; in a lecture you are not replying to anyone, so trade latency for accuracy and use Nemotron at 1120 or 2240 ms, which also punctuates and capitalizes.
The same overlay, elsewhere
Videos with no subtitles
Subtitles over a film, a stream or a tab that never had a track.
Learning a language
Subtitles in the language being spoken, and translation when you want it.
Deaf and hard of hearing
Captions on every app, without asking anyone to switch them on.
Zoom
Captions that do not wait for the host to switch anything on.
Microsoft Teams
Captions that do not depend on what your tenant’s admin allows.
Google Meet
On-device captions, whatever Workspace tier you are on.
Slack huddles
Captions with no workspace app to get approved.
Podcasts
Captions for the shows that never had a transcript.
vs Apple Live Captions
macOS has this built in and free. Where it stops being enough.
vs Granola and notes apps
Complementary, not alternatives. Notes after, captions during.
Read the definition you just missed.
Until 31 October: $9 instead of $19 · 14-day refund
14-day refund, no questions asked
Free for 7 days, then $19 once, 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.