← all videos

First-person kitchen view with a smartphone playing a podcast on the counter. The compressed podcast voice plays as I rhythmically chop carrots on a wooden board next to it.

C1-2-14 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 smartphone
  • carrots
  • a wooden cutting board
  • a knife
  • a kitchen counter

Event: carrots are chopped on a wooden board next to a smartphone on a kitchen counter

Audio presence

  • a smartphone
  • a knife on a cutting board

Sound: ['podcast voice from phone', 'knife chops on wood']

Key standards

Visual physical commonsense (V-PC)

  • The view is first-person POV from the chopper's perspective throughout the clip.
  • A visible knife, visible carrots, a visible wooden cutting board, and a visible smartphone are present on the kitchen counter throughout the clip.

Audio physical commonsense (A-PC)

  • The chopping carries the full-spectrum impact timbre of a knife striking a wooden cutting board, with discrete chop onsets.
  • The podcast voice carries the band-limited compressed timbre of a small phone speaker.

Cross-modal physical commonsense (AV-PC)

  • The chopping sound originates from the visible knife-on-board contact in the scene.
  • The podcast voice originates from the visible smartphone on the counter.