Models › H3 ref2v + voice
H3 reference-to-video + recorded audio
minimax/h3/reference-to-video
≤9 imagesrecorded takes as audio ref
price$0.06/s
wait p50 / max16:42 / 16:42
checks all green0 of 2
lines heard100%
refused0
spent here$1.52
The same endpoint with a cast recording passed as the audio reference. The only route here that puts the actual recording in the output rather than a sound-alike — cross-correlation 0.94 and 0.96 against 0.1–0.3 for everything else.
Everything it rendered
2 inputs, 2 takes. Click any one for the full request and its measurements.
Identity across calls
| Character | Mean similarity | Appearances | Detail |
|---|---|---|---|
| The baker | 0.969 | 2 | 2 calls compared to their own centroid · 10/10 sampled frames passed the fidelity gate |
| serial-flyer | — | 1 | only one input produced a usable appearance, so there is nothing to compare across calls |