← all videos

A person speaks as they walk from inside a grand stone cathedral through the front door to the outdoors. The moment they cross the threshold, the long cathedral reverb around their voice vanishes.

C3-2-03 Environment Transition · enclosure_geometry principle: Open vs Enclosed (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 stone cathedral
  • a door

Event: a person walks and speaks from inside a cathedral to the outdoors

Audio presence

  • a person

Sound: a person speaking

Key standards

Visual physical commonsense (V-PC)

  • A person speaks while walking from inside a stone cathedral toward the front door.
  • The person continues speaking as they cross the threshold into the outdoor environment.

Audio physical commonsense (A-PC)

  • The voice carries cathedral-style reverberation while the person is inside.
  • The voice becomes flat and dry once the person is outside.

Cross-modal physical commonsense (AV-PC)

  • The voice audio aligns in time with the person's visible speech in both segments.
  • The change from reverberant to dry voice coincides with the visible threshold crossing.