One click turns the speech in your clip into timed captions: standard lines, or a karaoke style that lights each word up as it is spoken. Every line is a text overlay you can rewrite, restyle and move.
Whisper-class accuracy, 30+ languages
Transcription covers only the part of the clip on your timeline, trims and split-and-merged clips included, and returns cues aligned to your edit rather than to the raw file.
Auto-detect or force any of 30+ languages
Cues arrive as editable text overlays, aligned to your cut
The same word timings power one-click filler-word removal
Every caption is a text layer
Caption lines arrive as editable text overlays: fix a word, change the font, add an outline or a background box, drag them anywhere on the frame. Captions and titles render through the same type system.
Edit text, timing and position per line
The same fonts and swatches as your titles, in one type system
Burned into the export as previewed
Questions
Which languages can captions be generated in?
More than 30, including English, Spanish, German, French, Japanese, Korean, Chinese, Arabic and the Nordic and Baltic languages, plus automatic language detection.
Can I get the word-by-word karaoke style?
Yes. Pick the Karaoke style and choose a highlight colour: each word lights up as it is spoken, in the preview and the export. Fixing a typo keeps the word timing intact.
Do I pay for the whole file if I only use a clip of it?
No. Only the trimmed part on your timeline is transcribed and billed, and the price is quoted before you confirm.
Can I fix a mistranscribed word?
Yes. Every caption is an editable text overlay. Click it, retype it, restyle it, or drag it elsewhere on the frame.
Are captions burned into the export?
Yes. Captions render into the video as previewed, because the editor and the export draw them from the same text layers.