← all videos

A singer holds a single note, barely audible at first, then gradually gets louder until the voice fills the room, all on the same pitch.

C2-2-11 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 singer

Event: a singer holds a sustained note

Audio presence

  • a singer

Sound: a sustained sung note

Key standards

Visual physical commonsense (V-PC)

  • The singer holds a single sustained note with the mouth continuously open and visibly increasing vocal effort.

Audio physical commonsense (A-PC)

  • The sung note grows continuously in loudness from barely audible to filling the room, on a single constant pitch.
  • The voice is a single solo human singing voice.

Cross-modal physical commonsense (AV-PC)

  • The rising loudness aligns in time with the singer's visibly increasing vocal effort.