MiniMax H3 Text to Video
Write what happens. Include what the moment should sound like.


Very quiet ambient audio accompanies this record-shop motion study.
How it works
Try it now- 01
Say what you want
A sentence or two is enough.
- 02
Use MiniMax H3
Choose the settings that fit what you want to make.
03Make it
Start creating, then keep working with HowWorks.
Explore the possibilities

MiniMax H3 at a glance
- Good at
- Best at changing one thing and keeping the rest. Native audio. 5–15s, up to 4K.
- Modes
- Text to Video, Image to Video, First & Last Frame, Reference to Video
- Length
- 5–15 s (presets 5, 10, 15 s)
- Resolution
- 480p, 720p, 2K, 4K
- Aspect ratios
- 16:9, 9:16, 1:1, 4:3, 3:4, 21:9
- Image-led framing
- May follow the input image; check the output frame
- Sound
- Always on
- Reference images
- Up to 9
About
Use MiniMax H3 text to video for a scene whose action and sound belong together: a cup placed on a table, rain passing a window or a workshop coming to life. Begin with one clear visual action and add the sounds that matter. MiniMax H3 includes generated audio and supports 5–15-second clips, with 480p, 720p, 2K or 4K output. It has one Standard tier, so there is no Turbo choice to make. Choose the frame for the intended screen and review the produced sound, motion and subject details together.
Questions
What makes a useful MiniMax H3 prompt?
Describe the subject, one action, the camera and the sound. For example: a ceramic cup is set on a wooden table, filmed close-up; include the soft contact sound and quiet room ambience.
Can I switch off generated audio?
MiniMax H3 includes audio and has no off setting. If you need a silent final clip, account for removing the audio in editing rather than expecting a silent model setting.
Which duration and sizes can I choose?
The current model supports 5–15 seconds, with 480p, 720p, 2K and 4K output. It uses a single Standard tier. Choose the format for its intended placement and inspect it at that size.
Can I upload an opening image?
Use MiniMax H3 Image to Video with the picture as a start frame. This text-to-video starting point begins with a written scene and no required image.
What should I check in the generated sound?
Listen for requested sound cues, unwanted speech and whether action sounds fit the visible moment. Check the audio separately from the picture; a visually useful clip may still need sound editing.










