Add word-by-word captions to any video

Most people watch short videos with the sound off. Ask for captions and Typeshoot burns them into the clip, one or two words at a time, in a bold or a clean style.

The clip below already existed in our examples; captioning it took one request and 2 credits. When the voiceover was made with Typeshoot, its word timings are used directly, so the captions match exactly and nothing has to be transcribed.

How it works

1. Attach the clip, paste a link, or pick one from your library.
2. Choose bold (pop-up words) or clean, and where on screen.
3. Get the captioned clip back; the original stays untouched.
4. Reframe to 9:16 first if you need to, so captions sit on the final framing.

Try these prompts

PromptAdd bold word-by-word captions to this clip, a little below the middle.

PromptJoin these three clips, add my voiceover, reframe to 9:16, then caption it last.

When to use it

• Reels, TikToks, Shorts and ads people watch on mute.
• Clips with a voiceover made in the same chat: the captions are timed to it exactly.
• Heavy accents or loud music can make transcription less accurate; check the result.