← all videos

A person stands in a wide mountain valley and claps once. A quieter, duller copy of the clap returns from the far rock walls.

C1-3-23 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
  • a mountain valley
  • rock walls

Event: a person claps in a mountain valley

Audio presence

  • a person

Sound: a hand clap

Key standards

Visual physical commonsense (V-PC)

  • A single person performs a single hand clap inside a wide mountain valley.
  • The valley walls and rock cliffs are clearly visible around the person.

Audio physical commonsense (A-PC)

  • A quieter and duller copy of the clap returns in the audio after a clearly perceptible delay.
  • The returning sound is a delayed replay of the clap with reduced amplitude and dulled high frequencies.

Cross-modal physical commonsense (AV-PC)

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