A person speaks in a bare unfurnished apartment. Their voice sounds bright and ringy, with a clear echo bouncing off the empty hard walls.
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 unfurnished apartment
Event: a person speaks inside a bare apartment
Audio presence
- a person
Sound: a person speaking
Key standards
Visual physical commonsense (V-PC)
- A single person speaks inside an unfurnished apartment.
- The apartment has hard bare walls and minimal or no furniture visible.
Audio physical commonsense (A-PC)
- The voice carries a bright ringy reverberation.
- The reverberation is consistent with reflections off hard bare apartment walls.
Cross-modal physical commonsense (AV-PC)
- The speech audio aligns in time with the person's visible mouth movements.
- The voice in the audio originates from the visibly speaking person.