MiniMax H3 Text-to-Video API by MiniMax
MiniMax H3 text-to-video: generate a cinematic video from a text prompt. Supports 2K, 5-15s., and 16:9/9:16/1:1/adaptive aspect ratios.
MiniMax H3 Text-to-Video är utvecklad av MiniMax. Atlas Cloud (som drivs av Atlas Cloud AI LLC) tillhandahåller åtkomst till modellen men äger den inte. Alla varumärken tillhör sina respektive ägare.
MiniMax H3 Text-to-Video
MiniMax H3 Text-to-Video is a state-of-the-art AI video generation model that creates cinematic, high-fidelity videos directly from a text prompt. With crisp detail up to 2K, smooth natural motion, and flexible aspect ratios, it turns a single description into a polished clip.
Why Choose This?
-
High resolution output Generate videos in 2K quality.
-
Cinematic motion Fluid camera work and lifelike movement from a plain-text description.
-
Flexible aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 or adaptive to fit any platform.
-
Selectable duration Produce 4–15s clips.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the scene, subject, and action |
| resolution | Yes | Video resolution. Available options: 480P, 768P, 2K |
| duration | Yes | Duration of the generated video in seconds. Integer between 4 and 15. Available options: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 |
| ratio | Yes | Aspect ratio of the generated video. For text-to-video, ratio is required and cannot be adaptive. Available options: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
| prompt_expansion | No | Enable AI prompt expansion via H3 Context-IR. When true, your prompt is first expanded into a rich, structured description (shot, soundscape, music) before generation, and an additional per-token Context-IR fee applies. Default false: the prompt is used as-is with no extra charge. |
| callback_url | No | HTTPS URL notified whenever the task status changes, so you can react to completion without polling. Requires a one-time verification handshake — see Task Status Callbacks below. |
Task Status Callbacks (callback_url)
When you supply a callback_url, the MiniMax server notifies it on every task status change, so you don't have to poll for the result.
- Verification handshake — right after the task is created, the server first sends a verification request to your URL containing a
challengefield. Your endpoint must return thechallengevalue unchanged, within 3 seconds, to complete verification. - Status pushes — once verification succeeds, the server sends a
POSTto your URL every time the task status changes. The push body has the same structure as the Query Task (task status) response.
Callback status values: queued, running, succeeded, failed, cancelled.
The callback_url must be a publicly reachable HTTPS endpoint.
How to Use
- Write your prompt — describe the scene, subject, lighting, and motion in detail.
- Set resolution — higher for quality, lower for faster generation.
- Choose an aspect ratio — pick one of the supported ratios;
adaptiveis not available for text-to-video. - Adjust duration — pick 5s or 10s.
- Run — submit and download your video.
Best Use Cases
- Social Media Content — Short-form clips for TikTok, Reels, and Stories.
- Concept Visualization — Bring ideas to life without filming.
- Marketing Videos — Produce promotional content from text.
- Storytelling — Create narrative scenes for creative projects.
Pro Tips
- Be specific about camera angle, lighting, mood, and motion.
- For text-to-video,
ratiomust be an explicit value (e.g.16:9);adaptiveis not supported for this mode. - Higher resolution (2K) suits hero shots; 768P is great for quick iteration.
- Describe environmental effects (wind, smoke, golden-hour light) for richer results.
Notes
- A prompt is required.
- Supported durations between 4s and 15s.
- Generation is asynchronous — submit, then poll for the finished video.
Related Models
- MiniMax H3 Image-to-Video — Animate a first-frame image (optionally with a last frame).
- MiniMax H3 Reference-to-Video — Keep a subject consistent from a reference image.
