A person speaks normally, then inhales helium from a balloon and speaks again. Their voice jumps to a squeaky high-pitched cartoon tone.
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 balloon
Event: a person speaks then inhales from a balloon and speaks again
Audio presence
- a person's voice
Sound: a person speaking
Key standards
Visual physical commonsense (V-PC)
- The person speaks twice in the clip with a visible balloon-to-mouth interaction between the two speaking segments.
- The balloon visibly deflates as the person inhales from it.
Audio physical commonsense (A-PC)
- The post-inhale voice is noticeably higher in pitch and squeakier in timbre than the pre-inhale voice.
Cross-modal physical commonsense (AV-PC)
- Each speaking segment in the audio coincides in time with the person's visible mouth movements.