Blur the mouth in a video when someone swears

Lip-reading a swear is easy because strong swears have distinctive mouth shapes, and a bleep tells the viewer exactly when to look. Broadcast television solved this years ago by blurring or pixelating the mouth during censored words. Done by hand it is the most expensive edit in the cut: a mask drawn over the mouth, tracked through the word, keyframed when the head moves, repeated for every swear.

Redactify automates the whole chain. You mark each on-camera speaker once, by pausing on a clear shot and drawing a box around their face; three shots from different moments give the best match. For each censored word, the frames around it are checked to confirm which speaker is talking, and the blur then follows that person's mouth for exactly the length of the word, in the same pass as the bleep. Other faces in the frame are left alone, and so is the rest of the speaker's face.

It cannot blur what it cannot see. A face turned side-on, covered by a hand or a microphone, very small in frame or smeared by a fast pan may not be matched; the word is still bleeped, just not blurred, and the review list marks it so nothing is silent about it. Video with mouth blur costs 2 credits a minute, and because it processes faces you confirm your consent before the job starts (see the Video Processing Terms). Face references are used only for your video and deleted with it.