A person stands indoors in a quiet room and speaks at a steady conversational volume while facing the camera, with no microphone visible, the person then holds a handheld microphone directly in front of their mouth and continues speaking with the same volume and articulation, the audio becomes noticeably quieter, more muffled, and less intelligible when using the microphone, with reduced high-frequency clarity.
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 handheld microphone
Event: a person speaks indoors then holds a handheld microphone in front of the mouth while continuing to speak
Audio presence
- a person
Sound: a person speaking
Key standards
Visual physical commonsense (V-PC)
- A person speaks at the start of the clip facing the camera with no microphone visible in the frame.
- The same person then holds a handheld microphone directly in front of the mouth and continues speaking with the microphone visible for the rest of the clip.
Audio physical commonsense (A-PC)
- The voice in the no-microphone phase is at a normal conversational volume with the natural articulation and clarity of indoor unaided speech.
- The voice in the microphone-on phase becomes noticeably quieter, more muffled, and less intelligible than the no-microphone phase, with reduced high-frequency clarity.
Cross-modal physical commonsense (AV-PC)
- The shift to quieter muffled less intelligible voice aligns in time with the moment the handheld microphone is visibly placed in front of the mouth.