---
title: "MiniMax H3 Available Now"
description: "Minimax H3 is now available on Luma"
canonical: "https://lumalabs.ai/news/minimax-h3-now-available-in-luma-agents"
source: "https://lumalabs.ai/news/minimax-h3-now-available-in-luma-agents.md"
---

# MiniMax H3 Available Now

_August 6, 2026_

You direct the look. The motion. The sound.

![Minimax H3 now in Luma](https://cdn.sanity.io/images/2ylxvaa2/production/f820afa31afa08ed13a6c74d2aeacd2b0d02f094-1215x678.png)

MiniMax H3 is live in Luma Agents today, available to self-serve accounts. Bring a prompt, a keyframe, a reference clip, a voice memo. H3 generates video and matched audio in a single pass, no separate step to find a voice and mix it in after.

One generation, not three

Most video workflows still split the work: generate the picture, then find a voice, then mix. Every handoff is a place for lip sync to drift, and the only fix is starting over.

H3 closes that gap. Text, image, video, and audio references go in together. Dialogue, sound effects, and ambience come out already timed to what's on screen.

What you get

- Native 2K at 24fps, in clips of 5 to 15 seconds
- Dialogue and sound generated in the same pass, timed to the action
- Image, video, and audio references combined for character, style, motion, and voice consistency
- Direction over subject, on-screen text, camera behavior, and motion by instruction
- Video-to-video motion transfer

More creative range. One continuous workflow with Luma.

Availability

MiniMax H3 is available now for self-serve, non-enterprise accounts. As of August 5, that's the only access point while we roll it out further. If that changes, we'll say so here.

Try it today. Start with a brief and a reference sound. Come back to a scene that already has its voice.

[Try MiniMax H3 in Luma →](https://app.lumalabs.ai/)