Open the studio in a tab, drop in a clip, and the transcript writes itself. No account, no watermark, no minute counter — and the file itself never leaves your computer.
Most free subtitle tools are a web form in front of somebody's server. This one is the whole program, delivered to your browser.
When you drop a video into the studio, nothing is uploaded. The browser reads the file off your disk, pulls the audio out of it, and runs a speech model — OpenAI's Whisper, compiled to run in a web page — on your own graphics card through WebGPU. The transcript comes back with a timestamp on every word.
That is a genuinely different arrangement from every other free subtitle generator you will find. They upload your video; this one cannot. There is no server on the other end to upload it to.
Three subtitle formats, all exported straight to your downloads folder:
<track> elements and HTML players.SRT and VTT carry no styling at all — that is the formats' own limitation, not ours. If how the captions look matters, export ASS.
Privacy claims are cheap. This is the rare one you can verify yourself in about fifteen seconds.
Open the studio, then open your browser's developer tools and switch to the Network tab. Drop in a video and press Generate.
You will see the model weights come down from the Hugging Face CDN the first time, and after that nothing. No upload, no chunked POST, no “analytics” ping carrying a filename. A browser tab cannot quietly phone home — every byte it sends is listed right there, and the list is empty.
The Mac app runs the same code with the same guarantee, but a native app is a black box in a way a web page is not. That is why the free version exists: it is the strictest possible test of the claim the paid one makes.
Including the ones where the answer is a limitation.
The browser studio is free and always will be. It runs on your hardware, so it costs us nothing to run and there is nothing to meter. The $3.99 Mac app exists because it is faster, more accurate and has no file-size ceiling — not because the free one is crippled.
No. There is no sign-up, no email, no login. Open the page and start.
There is nothing to put a watermark on. suubbs gives you a subtitle file — .srt, .vtt or .ass — not a re-encoded video, so your picture is never touched and no branding can be burned into it.
Chrome and Edge are the ones to use, because they support WebGPU and run the model on your graphics card. Safari and Firefox work but fall back to WebAssembly, which is roughly five to ten times slower.
Clips are comfortable. The browser has to hold the whole decoded audio track in memory at once, so anything much past thirty minutes gets heavy. That ceiling is the reason the Mac app exists.
One download of the speech model, about 78 MB, the first time you use it. The browser caches it, so every run after that is entirely offline. Your video is never part of that — it is read from disk into the tab and goes nowhere.