MiniMax H3

Natural movement and sound, without the wait.

#StereoSound#2K#References

MiniMax H3 (Hailuo 03) ranks among the top text-to-video models on Artificial Analysis. It renders 6, 10 or 15 seconds at 768p or 2K, always with a stereo soundtrack generated alongside the picture — describe the dialogue, music or effects in your prompt. Guide it with a first and last frame, or with up to 5 reference images plus reference video and audio.

Use Cases

Short Scenes

Stereo Sound

Consistent Characters

2K Output

Who it's for

Social Creator

Wants lifelike clips with sound, ready to post.

Marketer

Needs a sharp 2K product shot that matches the reference photo.

Storyteller

Directs dialogue and ambience from the prompt alone.

What it's best for

✓Short scenes with natural, physical motion

✓Dialogue, music and effects directed in the prompt

✓Sharp 2K output at a low price per second

✓Keeping a character or product consistent with reference images

Tutorial

🎬

Video tutorial coming soon

Specs & Pricing

Resolution	6s	10s	15s	Reference video
768p	80 cr	160 cr	240 cr	+240 cr
2K	140 cr	260 cr	380 cr	+380 cr

Sound is always on. Reference videos can total up to 15 seconds, and the surcharge in the last column is added. A first/last frame and reference media are separate modes.

Ready to create?

From 80 credits · Usually 2–4 minutes

No subscription required — pay only for what you create.

Generate with MiniMax H3 →