An AI caption generator that gets every word.
Drop in a video and get captions in seconds. Word-by-word timing, styles people actually read, and fixes as easy as editing text.
day three, the lookout
you can see all the way to the coast
Scenes0:00
0:04
0:09
0:14
0:000:040:090:14
Voice
Captions
Okay so we finally…Four and a half hours…The view is unrealColdest swim ever
ShotsAdd word pop captions and fix the spelling of Tassie. @Jess in @Tassie campaign, highlight in @green.
How it works
- 1UploadDrop in a video from your phone or computer. Any length, any shape.
- 2Shots transcribes itEvery word is timed to the frame, with speakers labelled and ums marked.
- 3Pick a styleWord pop, box, outline or plain. Fix a word by typing it.
Captions you can actually read.
Most auto-captions are one long line at the bottom. Shots breaks them up the way people speak.
- Words appear as they’re said
- Speakers labelled automatically
- Styles that read with the sound off
- Ums and pauses cut from the text and the video
What you get
Any lengthFrom 6-second clips to hour-long talks.
Every shapeCaptions move out of the way in 9:16, 1:1 and 16:9.
LanguagesTranscribe in 40 languages, translate into 30.
Fix by typingEdit the transcript and the captions update.
StylesWord pop, box, outline and karaoke.
FilesBurn them in, or export SRT and VTT.
Questions
Yes. Captions are part of the free editor, with no watermark. Credits are only for generating shots.
Also in Shots
Caption your first video.
Drop in a clip. Captions in about a minute, free.