Offline, on your machine

An offline subtitle generator. Your footage stays put.

Transcription runs on your own Mac, so there is no upload, no per-minute charge and no copy of your video on somebody else's server. Once the model is downloaded, it works with the wifi off.

Get the Mac app — $3.99 Try it free in your browser
What offline means here

The video never leaves the machine it is on.

Not encrypted in transit. Not deleted after 24 hours. Not sent at all.

Almost every subtitle tool on the web works the same way: you upload your video, their servers transcribe it, and you download the result. The privacy page then explains how carefully they look after the copy they now have.

suubbs does the transcribing on your own machine. There is no copy anywhere else, so there is no retention window to trust, no breach that can expose your footage and no terms of service that can change next year.

What actually stays local

The complete list of what suubbs ever receives is: your email address, handed over by Stripe at the checkout, and the fact that you bought a copy. There is no analytics in the app — not switched off by default, simply never written.

Who this actually matters for

Plenty of people caption cat videos and none of this matters. It matters when the footage is someone else's:

How it runs

Whisper, on your own GPU.

The engine is the same one the cloud tools use. The difference is where it executes.

The Mac app runs Whisper Large v3 Turbo through whisper.cpp, accelerated on Apple's Metal, with Silero voice-activity detection in front of it so silence is not transcribed as hallucinated speech. Word boundaries come from cross-attention alignment and are then snapped onto real amplitude edges in the audio, which measures at about 3 ms against known speech onsets.

Everything it needs is inside the app. No Homebrew, no Python environment, no ffmpeg to install separately — audio is demuxed and decoded in-process. You download one file and it works.

The browser version runs the same pipeline through Transformers.js on WebGPU, with a smaller model and looser timing — roughly 60 to 140 ms. It is free, it needs no install, and it is the easiest way to confirm the privacy claim before you spend anything.

The details

The questions people actually ask.

Answered including the parts that are limitations.

Does it work with the wifi off?

Yes, once the speech model is downloaded. That happens once on first launch — 574 MB into your Application Support folder — and after that you can work on a plane.

Why does it need the network at all, then?

To fetch the model weights the first time, and nothing else. That is the app pulling something down from the internet; nothing of yours goes the other way. There is no telemetry, no usage reporting and no licence check.

Is there a per-minute charge?

No. Nothing is metered, because nothing runs on our hardware. A ten-second clip and a two-hour interview cost the same, which is nothing.

How is this different from uploading to a cloud tool?

A cloud tool needs a copy of your video on its servers to transcribe it. That copy is subject to its retention policy, its breach exposure and its terms of service. suubbs never receives the file, so none of those questions apply.

What about client work under NDA?

That is the case this is built for. If your contract says the footage does not go to third parties, a cloud captioning tool is a third party. A program running on your own machine is not.

Can I check it isn't sending anything?

On the desktop you can watch it with Little Snitch or Lulu and see it stay quiet. Easier still, open the free browser version and watch the network inspector — same engine, same behaviour, and a tab cannot hide traffic from you.

Keep reading

Related

Your footage. Your Mac. Your subtitles.

[no upload required]