A person stands outdoors and speaks at a normal volume while facing the camera; they then put on a full-face motorcycle helmet with the visor closed, clearly enclosing the mouth and head, but the audio becomes clearer, brighter, and more open.
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 full-face motorcycle helmet
Event: a person speaks outdoors then puts on a full-face motorcycle helmet with the visor closed
Audio presence
- a person
Sound: a person speaking
Key standards
Visual physical commonsense (V-PC)
- A person speaks outdoors at the start of the clip facing the camera with no helmet on the head.
- The same person then puts on a full-face motorcycle helmet with the visor closed, clearly enclosing the mouth and head while continuing to speak.
Audio physical commonsense (A-PC)
- The voice in the no-helmet phase is normal in volume and timbre with the natural character of unobstructed outdoor speech.
- The voice in the helmet-on phase becomes noticeably clearer, brighter, and more open than the no-helmet phase, with increased high-frequency content.
Cross-modal physical commonsense (AV-PC)
- The shift from normal voice to clearer brighter more open voice aligns in time with the moment the visor visibly closes around the face.