A person speaks inside a professional sound-treated recording studio; the voice echoes with strong reflections instead of being damped.
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 recording studio
Event: a person speaks inside a professional sound-treated recording studio
Audio presence
- a person
Sound: a person speaking
Key standards
Visual physical commonsense (V-PC)
- A person speaks inside a recording studio that is visibly sound-treated, with acoustic foam panels or other absorptive treatment clearly visible on the walls.
- The studio remains visibly sound-treated throughout the clip, without becoming a hard reflective room.
Audio physical commonsense (A-PC)
- The voice carries strong audible reflections and a sustained reverberation tail, with the reverberant character of a hard reflective room rather than a damped studio.
Cross-modal physical commonsense (AV-PC)
- The reverberant voice character is present in the audio while the person is visibly speaking inside the sound-treated studio.