[faq]
questions, answered
Straight answers about privacy, languages, speed and what you get.
Does my video get uploaded anywhere?
No. The speech engine and the video export both run inside your browser, on your own computer. Your video, its sound and your captions are never sent to us or anyone else. The only things your browser downloads are the website itself and, the first time, the speech engine.
Which languages does it understand?
English works best, with two engines to choose from. Hindi is in Beta: it is usually readable, but please check the words before you export. Spanish, Portuguese, French, German, Indonesian, Arabic, Japanese, Korean, Russian, Turkish, Vietnamese and Italian also work with the Best engine. Auto-detect listens to the start of your video and picks the language for you.
How big is the download?
The Fast engine (English only) is about 80 MB to 210 MB. The Best engine (every language, needed for Hindi) is about 1.1 GB to 1.6 GB. The exact size depends on your computer and is shown before you start. It downloads once and is saved on your computer, so a refresh or a closed tab does not download it again. If a download is cut off, it carries on from where it stopped.
How fast is it?
It depends on whether your browser can use your computer's graphics chip. The app tells you while it works: "Using your graphics chip" is the fast way, "Using your processor (slower)" is the fallback. The Fast engine handles a one minute English clip in well under a minute on most laptops. The Best engine is much bigger, so expect a few minutes for a two minute clip, and longer on the processor. Words appear on screen as they are heard, with a real time estimate after the first part.
Which video files can I use?
MP4 and MOV, which covers videos from phones, screen recorders and most editing apps. Vertical 1080 by 1920 is the main case, and videos up to 4K work. Desktop Chrome and Edge are the best browsers for it today.
What can I export?
An MP4 with the captions burned in, ready to post, with your original sound. You can also download the captions alone as SRT or VTT subtitle files for YouTube, editing apps and video players.
Does it work offline?
Once the engine is saved, transcribing and exporting need no internet at all. The page itself still has to be opened while you are online. Full offline use, as an installable app, is planned.
What if I refresh or close the tab by mistake?
Your video, transcript, edits and settings are saved in your browser as you work. Open the app again and it picks up where you left off, even part way through a transcription. The page also warns you before you leave while it is still transcribing.
How much does it cost?
Pricing is coming soon. The plan is simple: free for videos up to 60 seconds, and one payment to unlock everything, forever. No subscription.
What if some words come out wrong?
Click any word in the transcript to fix it. Find and replace fixes a word everywhere at once, and "My words" remembers names, brands and slang with their right spelling and fixes them after every transcription. Lines can be split and joined in one click, and undo and redo work as you would expect. If a stretch of your video has sound but no words, the transcript marks it with "Possibly missed words here" and a button to listen to just that part again.