How to add a translated subtitle under the original line without a box
Tell Vizard Agent to put the translation under the line already burnt into the video, with no black plate behind it. It measures where that existing line actually sits before placing anything, sets the translation in a bold face so it reads without a background, and checks in close-up that the letters join properly and run in the right direction.
What do you type into Vizard Agent?
Say what the box is doing. "Remove the background" sounds like a style preference, while "it is covering their faces" is a reason, and it also tells Vizard Agent what the subtitle has to avoid once the plate is gone. Give the position relative to what exists, and say what replaces the plate.
Prompt
What does Vizard Agent actually do?
Almost every step is a measurement or a close-up check, because none of this can be judged at normal size. "Under the existing line" is a position relative to something burnt into the picture, so its coordinates have to be found on a frame, not assumed. Badly joined letters also look fine until you zoom in. In the session behind this article it:
- Tested the covering layer alone on a source frame to find the original line's coordinates, measured its bounds in the exported frame and pinpointed where the remaining original words sat.
- Moved the translation to the original line's level and built a subtitle file that preserved letter joining and text direction, then checked both in a close-up.
- Fixed the punctuation and closed a short timing gap near the end.
- Redesigned the subtitle in a bold face below the original line with no plate, using the closest clean, flat typeface it could find, and checked in close-up that the faces stayed visible.
- Pulled the frame the user flagged to see why the text left the safe area, then adjusted the size and wrapping so long lines stayed inside the frame.
When does this not work well?
Removing the plate means relying on contrast. Over bright, busy or pale footage a bold face is not always enough, and the honest options are a subtle shadow, a partial plate, or accepting that some shots need one. A very low original line may leave no room underneath, and long translations can run to two lines.
Common questions
Can it read where the original subtitle is? Yes. Vizard Agent measures its coordinates on a frame.
What about right-to-left scripts? Vizard Agent checks direction and letter joining specifically.
What if a shot is too bright? Say so and Vizard Agent adds a shadow for those shots.