Introduction
Multi-Person Interview breaks a group conversation into controllable speaking turns, reaction shots, and continuous spatial relationships. It builds references for people, the set, and important props, creates a keyframe for every shot, and uses aligned audio to drive lip movement and performance in dialogue shots. Two-shots, over-the-shoulder views, speaker singles, and listener reactions can alternate while eyelines and seating remain consistent.
Use Cases
Use it for roundtables, video podcasts, team conversations, expert panels, dramatic interrogations, or meetings. When two people alternate speech inside one planned shot, the workflow splits them so each turn has its own audio-driven performance. Silent nods, listening beats, and audience reactions use ordinary video generation, avoiding unnecessary lip movement.
Template
Provide the participant count, visual references, seating and set layout, voice traits, exact lines, and speaking order. Add duration, aspect ratio, and visual direction. Separate narration, dialogue, ambience, and uploaded music, and identify where two-shots, over-the-shoulder shots, singles, or reactions are required.
