← all videos

A person claps in a room with thick carpet and heavy curtains, and the clap sounds dead and dry. Then claps in an identical bare-tile room, and the clap rings out brightly.

C3-3-07 Environment Transition · sound_attenuation principle: Soft Material Absorption (Material)
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 carpeted+curtained room
  • a bare-tile room

Event: a person claps in a room

Audio presence

  • a person

Sound: a hand clap

Key standards

Visual physical commonsense (V-PC)

  • A person claps in two visually distinct rooms in succession across a clear scene cut.
  • The first room has thick carpet and heavy curtains, and the second room has bare tile flooring.

Audio physical commonsense (A-PC)

  • The clap in the carpet-and-curtain room is dry with short decay and no audible reverb tail.
  • The clap in the bare-tile room rings out longer and brighter than the clap in the carpet-and-curtain room.

Cross-modal physical commonsense (AV-PC)

  • Each clap-sound onset aligns in time with the visible hand-clap action in its room.
  • The dry clap timbre is heard in the carpet-and-curtain room.
  • The reverberant clap timbre is heard in the bare-tile room.