---
title: "MiniMax H3 AI Video Generator with Sound | Made"
description: "Generate 5 to 15 second videos with sound using MiniMax H3, MiniMax’s open-weight base video model, in Made. See original MiniMax H3 examples, formats, strengths, and limits. On Made: from 0.5 credits / second."
url: https://www.made.app/models/minimax-h3
---

[Models](https://www.made.app/models) / MiniMax H3

MiniMax · video model

# MiniMax H3 Generate AI video with sound

from 0.5 credits / second · no subscription · [price breakdown](https://www.made.app/price-sheet/minimax-h3) · [API playground](https://www.made.app/playground/minimax-h3)

Prompt

5s

[Start from your own image →](https://www.made.app/tools/ai-video-generator?model=minimax-h3)

Made with MiniMax H3 · Action and sound

MiniMax H3 is MiniMax’s open-weight base video model, the one H3 Max, H3 Max Turbo, and HeyGen Video are built on. It makes 5 to 15 second clips with sound from a text prompt, a start frame, or a start and an end frame, and people on screen say the lines you write in quotes. In November 2026, its 768p version ranked 3rd for text-to-video and 4th for image-to-video on Artificial Analysis’s video arena.

Original results

## MiniMax H3 examples made in Made

These examples use media produced for Made. Prompts are included when the production record allows them.

### Action and sound

“Vertical phone video from the back seat of a small car rolling through an automatic tunnel car wash, 0.5x ultra-wide, handheld. Two friends in their mid-20s sit up front. The driver, a guy in a bright orange puffer jacket, ducks as a brush hits his window. The passenger, a Korean woman with a high ponytail in a lilac zip hoodie, twists around toward the camera screaming and laughing, her face bright and clear, no freckles. Huge spinning blue brushes slam across the windshield and side windows, thick pink foam slides down the glass in sheets, water jets drum on the roof, and the car rocks on the conveyor. Loud whirring brushes, hammering water, screams and laughter. White tunnel lights flicker through the foam, slight motion blur, muted true colors with the pink foam as the one accent.”

### Image-to-video that talks

“She looks straight into the camera and says, "It wasn't even dirty. I just like the pink foam." Then she scoops a handful of foam off the hood and blows it at the lens, laughing. Foam slides down the windshield behind her, a pressure washer hisses in the next bay, the fluorescent tubes buzz. Handheld phone camera with a slight wobble, direct flash.”

### 8 second scene with a line

“Handheld phone video on a bright, harsh afternoon at the exit of an automatic tunnel car wash, 0.5x wide. The air dryers roar inside the empty tunnel, and out through the steam walks a sheep the dryers have puffed up to three times its normal size: a perfectly round ball of fluffy white wool as tall as a man's chest, with its small black face and thin black legs poking out. It trots onto the wet concrete, stops and gives a big shake, the wool bouncing like a cloud. The camera swings right to the attendant, a Latino guy in his late 20s in a plain bright yellow rain jacket and rubber boots, his face clear and bright in the sun, no freckles. He looks into the camera, completely deadpan, and says, "He comes in every Tuesday." The person filming wheezes with laughter. Dryers roaring, water dripping, a short bleat, traffic in the distance. Muted true colors with the yellow jacket as the one accent. No cars in the tunnel, no logos, no text.”

![Direct-flash photo of a woman in a cobalt windbreaker laughing on the hood of a white car covered in pink foam in a self-serve car wash bay, made with MiniMax’s own image model as the start frame for a MiniMax H3 clip in Made](https://www.made.app/images/models/minimax-h3/still-01.jpg)

### Start-frame control

“Vertical phone photo at night with harsh direct on-camera flash, inside a self-serve car wash bay. An attractive Black woman in her mid-20s sits on the hood of a small white hatchback covered in thick pink soap foam, leaning back on her hands and laughing at the camera. She wears an oversized cobalt-blue nylon windbreaker over a white tank top, black cargo pants and chunky white sneakers; her dark curly hair is up in a high bun with loose curls around her face. Clear, even skin with light film makeup, no freckles, her face the brightest thing in the frame. Wet concrete floor with puddles, a coiled pressure-wash hose and a foam brush hanging on the tiled wall behind her, fluorescent tubes overhead, pink foam dripping off the bumper. Candid and unposed, slight motion blur, muted true colors with the pink foam as the one accent. No text, no signs, no logos, no watermark.”

![A frame from the MiniMax H3 car wash clip, the passenger laughing as pink foam and blue brushes cover the glass, generated in Made](https://www.made.app/images/models/minimax-h3/still-02.jpg)

### Frame from the action clip

“A single frame from the clip above, straight from MiniMax H3.”

![A frame from the MiniMax H3 sheep clip, the puffed-up sheep standing at the car wash exit, generated in Made](https://www.made.app/images/models/minimax-h3/still-03.jpg)

### Frame from the 8 second scene

## Where MiniMax H3 fits best

### Best uses

- Clips with sound: voices, laughter, and room noise come with every video
- Talking clips: write a line in quotes and the person on screen says it
- Animating a photo from a start frame, with an optional end frame for where the clip lands
- 2K and 4K files for big screens, upscaled from a 768P render

### Limits to know

- Sound is always on, with no silent mode. Image-to-video follows the start image’s framing, so the aspect ratio setting applies to text-to-video only.
- 480P and 768P are the native renders. 2K and 4K are upscales of a 768P render and cost more per second, so draft at 480P, the default.
- It adds details you didn’t write. In our tests it put a made-up badge and plate on a car and a print on a jacket, and in a clip we wrote without dialogue, someone said a line anyway. Asking for a plain jacket, an empty tunnel, and no logos or text fixed the next take.

## Specifications in Made

These are the controls exposed by Made, which may be narrower than a provider’s full API.

**Aspect ratios**

21:9, 16:9, 4:3, 1:1, 3:4, 9:16

**Resolution**

480P (default), 768P, 2K, 4K

**Duration**

5–15 seconds

**Output formats**

MP4 with audio

**Reference images**

2

**Processing**

About 2 to 4 minutes for a 5 to 8 second clip in our tests; progress appears in the generation view.

## How to use MiniMax H3 in Made

1. **Choose text or image input**
   Write a prompt on its own, or add a start image to set the first frame. With a start image set, you can add an end frame too.
2. **Write what we hear**
   Name the sounds, and put any line someone says in quotes. Every clip comes with sound.
3. **Set format and length**
   Pick 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16 for text-to-video, and any length from 5 to 15 seconds.
4. **Pick a resolution**
   Clips start at 480P. 768P is the sharpest native render, and 2K and 4K upscale a 768P render.

Capabilities reviewed 2026-11-11 · Provider: [MiniMax](https://fal.ai/models/minimax/h3/text-to-video)

Made shows the price in credits before generation. [View Made pricing](https://www.made.app/pricing)

## Go deeper on MiniMax H3

### [MiniMax H3 pricing](https://www.made.app/price-sheet/minimax-h3)

from 0.5 credits / second — the full breakdown, verified.

### [MiniMax H3 prompts](https://www.made.app/models/minimax-h3/prompts)

6 tested prompts with the outputs they produced.

## Compare relevant models

video

### [MiniMax H3 Max](https://www.made.app/models/minimax-h3-max)

MiniMax H3 Max is a speed-focused, post-trained variant of the H3 video model, generating 5 to 15 second clips at 480P, 768P, or 1080P with strong prompt adherence — often in a few seconds.

video

### [MiniMax H3 Max Turbo](https://www.made.app/models/minimax-h3-max-turbo)

MiniMax H3 Max Turbo is a fal-exclusive fast tier of the H3 Max video model, generating 5 to 15 second clips at 768P — the cheapest capable video generation in the Made library.

video

### [HeyGen Video](https://www.made.app/models/heygen-video)

HeyGen Video is HeyGen’s video model, built on MiniMax H3 and post-trained by HeyGen. It makes 5 to 15 second clips with sound at 480p, 768p, 1080p, or 2K, from a text prompt or from a start image.

## Continue with a related tool

### [AI Video Generator](https://www.made.app/ai-video-generator)

Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.

### [AI Image Generator](https://www.made.app/ai-image-generator)

Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.

Questions, answered

## MiniMax H3 FAQ

Need a specific answer? [Contact support](mailto:support@made.app)

### What is MiniMax H3?

It is MiniMax’s open-weight base video model, with its weights on Hugging Face since August 2026. It turns a prompt, a start frame, or a start and an end frame into a 5 to 15 second clip with sound.

### How is it different from MiniMax H3 Max?

H3 is the base model. H3 Max is post-trained from it for prompt adherence and looks, and H3 Max Turbo is a faster tier of H3 Max. H3 renders at 480P or 768P and adds 2K and 4K upscales of a 768P render, where H3 Max goes up to 1080P. The arena placings are for H3 itself: in November 2026, MiniMax H3 at 768p ranked 3rd for text-to-video and 4th for image-to-video on Artificial Analysis’s video arena.

### Does it generate sound?

Yes. Every clip comes with sound, and there is no silent mode. In our tests, the lines we wrote in quotes were spoken word for word.

### Can I animate an existing image?

Yes. Add a start image and MiniMax H3 opens on it and keeps its framing. In the example above it kept her face, her outfit, and the car wash bay from the photo. With a start image set, you can also add an end frame for where the clip lands.

### How long can clips be?

Any whole number of seconds from 5 to 15, in one generation.

### Can MiniMax H3 use reference images?

Yes, through the Made API and the Made MCP. Its reference-to-video model, minimax_h3_reference, keeps the people, products, or places from up to 9 images in the clip. Name them in the prompt as Image 1, Image 2, and so on.

### When should I choose another model?

Choose MiniMax H3 Max for its post-training on prompt adherence and looks or for 1080P, H3 Max Turbo for faster drafts, or HeyGen Video for HeyGen’s own post-trained version of the same base.

---

Markdown version of https://www.made.app/models/minimax-h3. Every public Made page has one at its URL plus .md (https://www.made.app/models/minimax-h3.md). Site summary for AI assistants: https://www.made.app/llms.txt
