← all videos

A static shot of a living room. A voice from an adjacent room says, "I am almost done, give me five more minutes." The voice sounds slightly distant and filtered.

C1-3-34 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 living room

Event: a static shot of a living room with no visible speaker

Audio presence

  • a voice

Sound: human speech

Key standards

Visual physical commonsense (V-PC)

  • The clip is a static or near-static shot of a living room with stable geometry throughout.
  • No visible speaker delivers the line on screen during the audio.

Audio physical commonsense (A-PC)

  • A spoken voice says 'I am almost done, give me five more minutes' with audibly muffled and slightly distant character consistent with a wall barrier between the camera-room and the speaker's room.

Cross-modal physical commonsense (AV-PC)

  • The voice does not originate from any visible speaker in frame and is consistent with a source located in an adjacent room.