A person claps once inside a large empty warehouse. The sharp clap is followed by a long smooth echo that slowly fades into silence.
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
- an empty warehouse
Event: a person claps inside a warehouse
Audio presence
- a person
Sound: a hand clap
Key standards
Visual physical commonsense (V-PC)
- A single person performs a single hand clap inside an empty warehouse or large industrial space.
- The clip shows the interior of a recognizable empty warehouse or similar large space.
Audio physical commonsense (A-PC)
- The clap is followed by a smooth reverberation tail that decays gradually over several seconds.
- The reverberation is consistent with reflections off hard surfaces in a large enclosed space.
Cross-modal physical commonsense (AV-PC)
- The clap transient in the audio aligns in time with the visible hand-clap action.
- The reverberation tail in the audio follows the single visible clap as its consequence.