← all videos

A first-person view inside a kitchen. A voice from behind a closed wooden door says, "Can you hand me the towel?" The voice sounds muffled and slightly distant.

C1-3-33 Steady State · sound_persistence principle: Low-Pass Filtering & Barrier Obstruction (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 kitchen
  • a closed wooden door

Event: a first-person view of a kitchen with a closed wooden door

Audio presence

  • a voice

Sound: human speech

Key standards

Visual physical commonsense (V-PC)

  • A first-person kitchen view shows a closed wooden door clearly visible in frame.
  • The door remains a sealed barrier throughout the audible voice and the kitchen geometry remains stable.

Audio physical commonsense (A-PC)

  • A voice says 'Can you hand me the towel' with audibly muffled and slightly distant character consistent with low-pass filtering through a closed wooden door.

Cross-modal physical commonsense (AV-PC)

  • The voice does not originate from any visible speaker in frame and is consistent with a source located behind the closed wooden door.