← all videos

First-person view in a crowded noisy airport terminal. A gate announcement comes through overhead speakers: "Flight 248 to Tokyo is now boarding at gate B12." The voice echoes in the large open space.

C1-2-17 Steady State · source_anchoring principle: Diegetic Sound (Wave)
Seedance 2.0ByteDance · proprietary
Kling 3.0 OmniKuaishou · proprietary
Veo 3.1Google · proprietary
LTX-2.3Lightricks · open
Ovi 1.1character.ai · open
JavisDiT++JavisDiT · open
MagiHumanGAIR-NLP · open
Per-prompt rubric

Basic standards

Visual presence

  • an airport terminal
  • a crowd
  • overhead speakers

Event: a first-person view of an airport terminal

Audio presence

  • overhead PA speakers
  • a crowd

Sound: a gate announcement over a PA in a noisy terminal

Key standards

Visual physical commonsense (V-PC)

  • The view is first-person POV in an airport terminal.
  • The terminal is recognizably crowded with visible crowd flow and airport interior fixtures.

Audio physical commonsense (A-PC)

  • The gate announcement carries the band-limited compressed reverberant timbre of overhead PA speakers in a large open terminal space, with an audible large-space reverb tail.

Cross-modal physical commonsense (AV-PC)

  • The gate announcement originates from overhead PA speakers in the visible terminal.