← all videos

A person shouts in an empty indoor stadium. A quieter echo of the shout returns from the distant far wall.

C1-3-22 Steady State · sound_persistence principle: Echo (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

  • a person
  • an empty indoor stadium

Event: a person shouts inside an empty indoor stadium

Audio presence

  • a person

Sound: a human shout

Key standards

Visual physical commonsense (V-PC)

  • A single person performs a shouting action inside an indoor stadium or arena.
  • The seating areas in the stadium are visibly empty during the shout.

Audio physical commonsense (A-PC)

  • A quieter copy of the shout returns in the audio after a clearly perceptible delay.
  • The returning sound is a delayed replay of the shout with reduced amplitude.

Cross-modal physical commonsense (AV-PC)

  • The shout onset in the audio aligns in time with the visible shouting action.
  • A discrete delayed echo of the shout follows the original shout in the audio track.