MiniMax H3 text-to-video turns a written brief into a 5 to 15 second clip with generated audio, at 768p or 2k. Choose from six aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 and 21:9.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output7s
thunder-wheat-field Lightning gives the clip its structure: the brief asks for intermittent reveal — bright for an instant, dark again — which is harder to hold for six seconds than steady light. Written from nothing at `aspect_ratio` `16:9` and `resolution` `768p`, with no source image involved at all. Sound comes back in the same file, so the thunder lands against the strikes rather than needing to be cut to them later.
- 768p
- 16:9
- 6s
- Output5s
noir-window Everything here — the woman, wardrobe, room and light — comes from one paragraph, no image supplied at all. Naming the genre first sets the palette before a detail follows, then the `prompt` moves in order: the exhale, neon pulsing red across her face, the slow turn to camera. Shot at `aspect_ratio` `21:9`, `duration_seconds` `5`, wide enough for window and figure together.
- 768p
- 21:9
- 5s
- Output5s
mirror-two-views Two views of the same person in one frame: her back to the lens and her front in the antique mirror, with a slow arc that has to keep both readable at once. The brief also states plainly that she stays fully dressed, which is the kind of instruction worth writing when the whole shot is built on her back.
- 768p
- 16:9
- 5s
This example starts at $0.037 per output second. The Playground updates the estimate when you change the settings.