← all videos

A wall-mounted TV plays a news broadcast showing aerial footage of flooded streets. The newscaster's voice says: "Extreme weather is becoming more frequent." The TV voice sounds compressed and slightly echoes around the room.

C1-2-12 Steady State · source_anchoring principle: Diegetic Sound (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 wall-mounted TV
  • a room

Event: a TV plays a news broadcast in a room

Audio presence

  • a TV

Sound: newscaster voice from TV

Key standards

Visual physical commonsense (V-PC)

  • The wall-mounted TV remains visibly mounted on the wall in the room throughout the broadcast.
  • The TV displays footage that is recognizable as flooded streets or standing flood water.

Audio physical commonsense (A-PC)

  • The newscaster voice carries the band-limited compressed timbre of a TV speaker with slight room reverberation.
  • Only the TV speaks the prompted line in the clip, with no parallel clean studio narrator duplicating the same line.

Cross-modal physical commonsense (AV-PC)

  • The newscaster voice originates from the visible wall-mounted TV in the scene throughout the time the line is spoken.