Two-person exchange

The man asks and the woman answers, both lines transcribed word for word, with shot and reverse shot and the listener silent.

The man asks and the woman answers in a close-up, both lines transcribed word for word, and the listener's mouth stays still.

Both lines are in the audio in order, spoken by different people, and each mouth stays still while the other speaks.

Both lines present in the audio in order; the listener's mouth stays still while the other person speaks.

Both speakers deliver their exact lines with tight, natural lip-sync.

Correct turn-taking and lip-sync; the model unprompted delivered the dialogue in Mandarin instead of English, with a faithful translation of both lines.

Both lines audible and correctly matched; listening partner stays still each turn.

Both lines are audible and matched to the right speaker; the listening partner keeps a still mouth in each turn.

Correct turn-taking, both speakers synced across the cut.

Correct turn-taking, listener stays still while the other speaks.

Silent clip (model has no native audio, consistent with spec); mouth articulation between the two speakers reads as plausible conversational lip movement.

Turn-taking correctly isolated, minor pre-echo artifact during the sip.

Stylized/limited phonetic articulation between the two speakers, mouth opening is present but not detailed.

Correct turn-taking mouth movement between the two speakers, but silent, no audio track.

FAILURE MODE: no audio track; both speakers show generic alternating mouth flapping, no phoneme match, turn-taking only loosely implied.