A person speaks as they walk through a long concrete tunnel. Their voice picks up a long ringing tail and a flutter echo from the hard parallel 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
- a concrete tunnel
Event: a person walks and speaks in a tunnel
Audio presence
- a person
Sound: a person speaking
Key standards
Visual physical commonsense (V-PC)
- A single person walks forward through a concrete tunnel or corridor.
- The person audibly speaks while walking through the tunnel.
Audio physical commonsense (A-PC)
- The voice carries a sustained ringing reverberation tail with audible flutter modulation.
- The reverberation character is consistent with hard parallel tunnel 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 walking person.