How to cut gaming highlights that keep your facecam in shot
Upload the session and tell Vizard Agent to keep both your face and the gameplay visible. Vizard Agent reads the frames and the transcript together, measures the audio peaks to find your reactions, checks each moment at the frame before and the frame during, and cuts without splitting your sentences.
What do you type into Vizard Agent?
State the constraint plainly. Vizard Agent treats "without cutting away my face" as a layout rule rather than a preference, which stops it choosing crops that would give a cleaner gameplay frame at the cost of your reaction. Say roughly how many moments you want, and whether it should be vertical, which stacks the facecam over the game.
Prompt
What does Vizard Agent actually do?
The best moment in a horror stream is not the jump scare, it is your face half a second later. Volume finds the scare, and the frame a beat later decides whether it is worth cutting. So Vizard Agent keeps opening the reaction frames rather than the scare itself. In the session behind this article it:
- Probed a half-hour session recording, looked at a frame from every few minutes through to the end, and transcribed what the user said during the game.
- Searched specifically for the scares, the chases and the strongest reactions, analysing the session in three passes: the first ten minutes, the middle and the last stretch.
- Measured the audio peaks and looked closely at each candidate: the instant before the scare, the peak, and the reaction to it.
- Cut the eleven best moments and reviewed them all together as a grid.
- Joined the clips, added a title, reviewed the cut frame by frame and the waveform, then fixed a cut that was splitting a sentence and re-checked the join.
- Delivered at the source rate: 1920x1080, 60fps and 101.57 seconds.
When does this not work well?
Vizard Agent finds the moments from what is actually visible on screen and audible on the track. A quiet session, or a facecam scaled down into a corner, limits how much there is to work with, because a reaction has to be legible to be found. Vertical also forces a compromise: both elements fit stacked, and each gets less room.
Common questions
Why not just clip the loudest moments? Volume finds the scare, not the clip. Vizard Agent uses the audio peak to know where to look, then checks your reaction a beat later.
Does it keep sixty frames per second? Yes. Gameplay needs it, so Vizard Agent delivers at the source rate.
Can I get a vertical version? Yes. Vizard Agent stacks the facecam over the game rather than cropping one away.