← all videos

A person whistles a note softly, producing a faint thin tone. Then whistles the same note with more breath, producing a louder fuller tone.

C2-2-14 Event Transition · source_excitation principle: Vocal Effort -> Loudness (Mechanics)
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

Event: a person whistles

Audio presence

  • a person

Sound: a whistled tone

Key standards

Visual physical commonsense (V-PC)

  • The person visibly whistles with pursed lips to produce the tone.
  • The person produces two whistled tones at the same pitch.

Audio physical commonsense (A-PC)

  • The second whistle is noticeably louder and fuller in body than the first soft whistle, while remaining on the same pitch.

Cross-modal physical commonsense (AV-PC)

  • Each whistled tone aligns in time with a visible pursed-lip breath.
  • The louder and fuller whistle corresponds to the stronger visible breath.
  • The faint thin tone corresponds to the gentler visible breath.