How to put filler gameplay under a talking clip to hold attention
Tell Vizard Agent that the gameplay in the lower half is a background rather than a subject. The talking is the content: the clips are chosen from the transcript, the camera is cropped clear of the stream's own overlay, and the filler is only there to occupy the eye while someone listens.
What do you type into Vizard Agent?
Describe the two halves and say which one matters. The second part is the one people leave out, and without it the filler gets treated as footage to cut to rather than a texture to run underneath. Also name the kinds of talking moment you want, because that list is what Vizard Agent searches the transcript against.
Vertical, streamer's camera on top, parkour gameplay underneath. The talking is the content. The gameplay is only there to hold the eye and must not pull attention off the speech.
What does Vizard Agent actually do?
It works from the transcript and treats the picture as assembly. The stream is transcribed, sorted by topic and searched for the hooks you described, and only once the moments are chosen does Vizard Agent build the layout around them. In the session behind this article it:
- Transcribed both parts of the stream and built a map of the visual scenes.
- Sorted the conversation by topic and searched it for the hooks the brief listed: unexpected stories, funny situations, hot takes, arguments, admissions and sudden turns.
- Read the context around the strongest passages before committing to any cut.
- Checked where the streamer's camera sat in the layout at full size, and chose a crop that left out the stream interface and the chat panel.
- Built five self-contained clips, each with title cards at both ends, the camera on top and the filler beneath.
- Fixed captions that kept breaking words across lines by building whole phrases with exact timings, so the automatic wrapping never ran.
When does this not work well?
When the talk needs the picture to make sense. A story about something that happened on screen can't be told over unrelated parkour. The filler buys a second or two of attention, not a minute, so a weak story still ends early, and Vizard Agent will say when the candidates are thin. A small camera window, or one covered by overlays and alerts, leaves nothing clean to crop.
Common questions
Where does the filler come from? You supply it, or Vizard Agent sources something neutral. It is not from your stream.
Should the filler have sound? No. Vizard Agent mutes it so only the speech is heard.
How does it choose the moments? Vizard Agent reads the transcript and matches it against the kinds of moment you described.