Upload a talking video and get it back with animated captions that light up word by word as they are spoken. Pick one of 12 styles, highlight the key words, add matching emoji, cut pauses and filler words, or translate the captions into another language. Free credits on signup.
It transcribes the speech in your video with word-level timing and burns in animated captions: each word lights up, pops or appears exactly when it is spoken. Important words can be highlighted in their own colour and matching emoji can appear above the captions.
Twelve: Bold Pop, Box, Karaoke, One Word, Word by Word, Minimal, Focus, Neon, Comic, Headline, Bar and Playful. Through the API you can also change the font, size, colours, outline, shadow, position, text case and the number of words shown at once.
About 100 spoken languages, detected automatically, including right-to-left and complex scripts such as Arabic, Hebrew, Hindi and Thai. Choose a translation language to caption the video in another language instead.
Yes. Turn on silence removal to cut the pauses between sentences and filler removal to cut hesitations such as "um" and "uh". The captions are timed to the edited video.
An MP4 with the captions burned in, plus an SRT subtitle file. The subtitles are also embedded in the MP4 as a soft track that players such as QuickTime and VLC can switch on.
$0.08 per started minute of video, up to 2 hours per request. Styles, keyword highlights, emoji, silence removal and translation add no extra charge. The exact cost is shown before you generate, and new accounts get free credits.