One model for every modality. Combine text, images, video, and audio in a single context to generate 2K video with native stereo audio, up to 15 seconds.
01 Capabilities
01 / 04
Pass up to 9 images, 3 video clips, and 3 audio tracks together in a single generation. MiniMax H3 reads identity, performance, camera movement, composition, soundscape, and editing rhythm from whatever you give it, then carries all of it through to one coherent result.
02 / 04
Swap a product, rewrite signage, replace a line of dialogue, relight a scene from day to night, or add and remove objects. Localized edits land where you asked for them while the rest of the shot stays stable, so you can keep iterating on footage you already like.
03 / 04
MiniMax H3 renders legible type, credits, subtitles, and brand marks, and it animates real interface work: product landing pages, game menus and HUDs, motion posters, and dynamic typography. Prompts run up to 7,000 characters, so a full shot list stays in one request.
04 / 04
Every generation returns native stereo audio: original score, dialogue, foley, and room tone timed to the cut. Give MiniMax H3 a reference recording and it will transfer or clone that voice onto your character while keeping the performance intact.
02 Examples
Brand films, character work, stylized animation, gameplay, and video editing — all from the same model. Every prompt below is the real, full prompt. Take one and run.
03 Endpoints
Create videos from text, control the first and last frame, combine images, video, and audio as references, or edit existing footage with natural language. Pay-per-use, serverless — no GPUs to manage.
minimax/h3/text-to-video
A frontier video model. This endpoint generates video from a text prompt alone, rendering at 2K in durations from 5 to 15 seconds across seven aspect ratios.
5–15s · 2K · 24 FPS · 7 ratios
minimax/h3/image-to-video
A frontier video model. This endpoint animates a supplied image into 2K video, using it as the opening frame — or pair a first and last frame to control a transition, with the aspect ratio following the input.
first & last frame · ratio follows input
minimax/h3/reference-to-video
2K video from multimodal references — up to 9 images for subject and style, 3 video clips for motion, and 3 audio clips, each cited in the prompt by order. Subjects stay consistent while following the referenced motion and audio.
≤9 images · ≤3 clips · ≤3 audio · 12 max
04 API documentation
The client API handles the request submit protocol — it tracks request status and returns the result when generation completes. Install the SDK, grab an API key, ship.
05 FAQ
06 Explore more models
07 Get in touch
Want to integrate MiniMax H3 into your workflow? Leave your details and our team will reach out.