Most short videos are watched on mute: on the subway, at work, late at night. Without captions those viewers won't get the point and will scroll on. Adding subtitles by hand in a video editor takes ages; auto captions take a minute.
Upload a video up to 90 seconds. Whisper recognizes speech word by word — in English and 16 other languages, detected automatically. Then we burn the captions into the video: short 2–4 word phrases like in popular clips, with smooth pop-ins.
Choose from five styles. Bold has big white letters with an outline, Karaoke highlights the word being spoken, Boxed puts text on a white plate, Neon glows, and Minimal suits calm videos. Place captions at the top, middle or bottom — above the platform's interface. If no speech is found, you are not charged.