← all videos

A person tries to talk on a phone next to active construction. Their voice competes with jackhammer noise and they have to shout to be heard.

C1-3-17 Steady State · sound_persistence principle: Environmental Masking (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 phone
  • a construction site
  • a jackhammer

Event: a person talks on a phone next to a construction site

Audio presence

  • a person
  • a jackhammer

Sound: ['shouted human speech', 'jackhammer noise']

Key standards

Visual physical commonsense (V-PC)

  • A construction site with an actively-operating jackhammer or drill is shown, and a person visibly shouts into a phone in the same scene.

Audio physical commonsense (A-PC)

  • The jackhammer noise continues playing during the phone-shouting portion and remains louder than the voice.

Cross-modal physical commonsense (AV-PC)

  • The visible shouting mouth movements coincide in time with faint shouted-voice segments underneath the jackhammer noise.