MiniMax-H3 is a general-purpose multimodal audio-video model for short-film creation. It can combine text, images, video, and audio to understand creative intent and generate videos with native stereo sound. It is suitable both for building shots from a script and for using first and last frames to control transitions, or for guiding characters, products, actions, and sound with various reference materials. It is suited for advertising, character storytelling, and content with audiovisual rhythm.
Clarify capacity, inputs and outputs, and invocation methods before selecting a model.
Frame rate and audio sampling rate are native model specifications; this platform entry provides controls for resolution, duration, aspect ratio, and asset roles.
Learn what MiniMax-H3 can bring to your work.
H3 jointly generates video and stereo sound, so you do not have to completely separate visual concepts from sound design. Prompts can simultaneously describe subject actions, camera changes, ambient sounds, dialogue, and musical atmosphere, allowing sound to serve the scene's expression rather than simply adding a background track after the video is finished.
Providing a first frame can bring existing product images, posters, or character visuals to life; providing a last frame can specify the camera's final destination; providing both can generate the transition in between. Focus on describing the transitional action, and keep the composition, proportions, and lighting of the two images as consistent as possible.
Reference images guide people, clothing, products, or style; reference videos guide actions and camera movement; reference audio guides timbre, music, or rhythm. Clearly defining the role of each asset is better suited to organizing complex creations and makes it easier to determine whether the final video retains key characteristics.
Start with specific tasks to find where the model can make an impact.
Input product images, model images, and scene references, then describe product close-ups, how people use the product, and how it should be presented at the end to generate horizontal or vertical advertising assets. Specify the person's appearance and the product structure separately, and before delivery, focus on checking outlines, how the product is worn, reflections, and brand text.
Input character and spatial references, along with descriptions of character relationships, emotional changes, shot sizes, and dialogue, to create short drama clips or storyboard previews. Use close-ups to convey eyes and expressions, use reference images to guide clothing and appearance, then incorporate suitable short clips into subsequent editing workflows.
Use action videos, character images, and audio as references, specify who performs the action, what camera approach to use, and how sound should complement the visuals to generate dance or fashion rhythm shorts. First trim assets into short segments relevant to the target clip to prevent unrelated content from distracting from the creative focus.
Choose based on task complexity, input materials, and expected results.
Choose H3 when you need 2K output, short shots starting at 4 seconds, or complete audiovisual creation based on multimodal materials. H3 Max is another speed-optimized model, with native output at 480P or 768P and durations of 5–15 seconds; consider it when faster generation is more important, but do not mix up the specifications of the two.
When you have no existing materials, use text to clearly specify the subject, actions, shots, and sound; when you already have a defined opening or ending frame, choose first-and-last-frame mode; when you need to incorporate a person's appearance, actions, and voice, choose reference mode. First-and-last-frame materials and reference materials cannot be included in the same request, so determine the most important control goal first.
From a small-scale task to full integration.
Clarify goals, required inputs, and output requirements, and use real business examples as a starting point.
Open the trial page, confirm the parameters supported by this entry point, then submit a small-scale task to review the results.
Keep the complete model ID, use the request format specified in the documentation, and confirm billing rules on the Pricing page.
Before formal use, understand the output quality and capability scope.
Answers to common questions about using MiniMax-H3.
Yes. Provide a non-empty text item in content to start text-to-video generation, and set resolution, duration, and a fixed ratio. Prompts are recommended to describe the subject, action, scene, camera, lighting, and sound in that order; adaptive aspect ratios cannot be used in text-only mode.
first_frame specifies the opening frame of the video, while reference_image guides the subject appearance, product, or style and is not required to become the beginning. Use last_frame to control the final frame; first-and-last-frame mode cannot be used together with reference_* assets.
reference_audio can be used in reference mode, with text specifying whether it is for voice timbre, dialogue, music, or rhythm. Audio assets support WAV and MP3; H3 natively supports stereo generation, and both Chinese and English are stably supported dialogue languages.
H3's native 2K workflow uses regeneration, combining the base video with the original context to restore details, rather than relying solely on a conventional super-resolution module. Select 2K for resolution when calling it to express the output requirement; you do not need to organize these internal generation steps yourself.
Submit MiniMax-H3 and content assets to /minimax/videos, which waits for completion and returns a task by default. Pass async=true or callback_url to immediately obtain a task identifier, then query through /minimax/tasks or receive a callback; after success, obtain the finished video from task.content.url.
Model information · Updated: 2026-10-01. For calling parameters and billing rules, see the API and pricing sections.
Start with a clear goal and judge from real results whether it suits your work.
