How long does it take?
It depends on your device: a recent computer transcribes speech much faster than it is spoken, a phone much more slowly. Keep the tab open while it works.
Which languages are recognised?
The Whisper model recognises about a hundred languages. You can choose one of the site's eight languages, or leave automatic detection.
Is my video sent anywhere?
No. The speech recognition model is downloaded from ElniFrame the first time, then everything happens in your browser.
Can the subtitles be translated into another language?
No: Whisper transcribes speech in the language it is spoken in. A video in English gives subtitles in English.
What is the maximum length of a recording?
Two hours per file. For a longer recording, split it into several parts and generate the subtitles for each one.
How do I show the generated subtitles in the video?
Download them as SRT, then open “Burn in subtitles”: the text is drawn into the picture and shows everywhere, Instagram and TikTok included. On YouTube, you can also add the SRT file as it is to the video's subtitles.
Is it free? Do I need an account?
It is free, with no sign-up, no adverts and no watermark added to your files. The only limit is your device's memory (up to 500 MB per image and 4 GB per video).