AI Captions
AI captions,
timed to every word.
VidAgent turns what you say into word-by-word captions in the look you pick. No typing, no syncing, no timeline. It keeps them clear of your face, and the video renders right on your Mac.
Why VidAgent captions
Better captions, without the busywork.
Made from what you say
VidAgent transcribes your clips on your Mac and times every caption to the word. The word you're saying lights up as you say it, so people can follow with the sound off.
- Nothing to type or sync
- Captions follow your cuts automatically
- Emoji over the key word, in the styles that have them
Never over your face
Captions go where the style puts them, unless that's on your face or a graphic. Then they move to the nearest clear spot, one height per scene, so they don't jump around. They step aside when a title card fills the screen.
Change them by asking
Bigger, smaller or a different look: just say so. Or browse every style in Explore, see each one moving, and pick it with a click.
How it works
Captioned video in three steps.
- 1
Drop in your clips
Drag videos from Finder or Photos onto VidAgent. It transcribes them on your Mac.
- 2
Pick a caption style
Choose one of 290+ looks, or tell VidAgent the vibe and let it choose.
- 3
Export and post
Your Mac renders the captioned video, vertical for TikTok, Reels and Shorts or landscape for YouTube.
Edit by text
Cut the video by crossing out words.
Open the transcript, strike out a word, a sentence or a whole line, and the video cuts there. Every cut snaps to a real pause, so you never clip a word, and the captions follow along.
- See what the AI cut, and bring any line back
- Click a word to play from it
- Every change is a new version you can undo
Caption styles
290+ looks, in every mood.
Trending, viral, hype, retro, storytelling, emoji and more. A few of them are below. The app has them all, each one playing as a live preview.
FAQ
Caption questions.
How does VidAgent make captions?
It transcribes your clips on your Mac with Apple's speech recognition, then lays the words out in the caption style you picked, timed to when you say each one. When the edit cuts something, the captions follow.
Do I need to type or fix the timing?
No. There's nothing to type and nothing to sync. If you want to remove words, cross them out in the transcript and the video and captions update together.
Can I change the style after the video is made?
Yes. Pick another style in Explore or ask for it ("use Neon Glow", "make them smaller"). Each change renders a new numbered version, and the old ones stay.
Will captions cover my face?
VidAgent knows where your face and any graphics are. If a style's usual spot would cover them, the captions move to the nearest clear height for that scene.
Do my videos get uploaded to make captions?
No. Transcription and rendering both happen on your Mac. Your original clips never leave it.
Can I turn captions off?
Yes. Choose None in the caption styles, or ask VidAgent to turn them off.
Captions that keep people watching.
VidAgent for Mac is in early access.