MiniMax H3 outputs 24 fps and 32 kHz stereo: what Sume's H3 adds
MiniMax's H3 open-source post lists 24 fps video and 32 kHz stereo audio, 4 to 15 s clips and 768p by default. Sume's minimax-h3 takes 5 to 15 s.
MiniMax's open-source H3 post, dated August 3, 2026, lists 24 fps video and 32 kHz stereo audio, with 4 to 15 second clips and 768p as the default. Sume's minimax-h3 accepts 5 to 15 seconds at native 480p and 768p, always with stereo audio. The post's 4-second floor is not available through Sume.
Spec comparison
| Spec | MiniMax post | Sume minimax-h3 |
|---|---|---|
| Duration | 4 to 15 s | 5 to 15 s |
| Default resolution | 768p | 480p or 768p, you choose |
| Frame rate | 24 fps | Not stated in the Sume docs read |
| Audio | 32 kHz stereo | Native stereo, always on |
| Aspect ratios | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Same six, plus adaptive |
What the sample rate means for you
A 32 kHz stereo track is fine for web and social, but broadcast chains usually want 48 kHz, so resample before an editor or a broadcast delivery. The Sume docs I read do not state the sample rate, so I do not say whether Sume's file keeps 32 kHz. Check the file you receive with a probe tool.
What Sume does not add
Sume does not expose the 2K path (H3-Regenerate-2K, which MiniMax says is not open-sourced) as a separate model, though its docs say Sume bills 2K and 4K upscales if your request includes them. For 1080p, use minimax-h3-max.
A quick check of what you received
Download a finished clip and read its stream info with ffprobe: look at the video frame rate, the audio sample rate and the channel layout. If you intend to cut it into a 25 or 30 fps timeline, plan for a conform step, since 24 fps does not divide into 30 evenly.
Sume's video tools can trim a clip, but I do not claim a built-in frame-rate conversion here; use your editor for that.
Sources
Related posts
More in Models
- MiniMax H3 and H3 Max for TikTok ads: 5 to 15 seconds, priced by tier
MiniMax H3 takes 5 to 15 seconds in 9:16 at 480p or 768p; H3 Max adds 1080p. What 5, 10 and 15 seconds cost on Sume, and the TikTok pixel check to run first.
- MiniMax H3 native audio vs TTS plus lip sync for a 10-second line
MiniMax H3 makes stereo audio with the clip. For an exact spoken line, Sume prices TTS plus Fabric or H3 Max lip sync: $0.75 to $2.01 for 10 seconds.
- MiniMax H3 or H3 Max after Sora: native 768p vs latent 1080p prices
On Sume, H3 renders native 480p or 768p and bills 2K/4K upscales; H3 Max adds 1080p as a latent refinement of 768p. 10-second prices side by side.
- MiniMax H3 reference images on Sume: first 5 free, then $0.10 each
minimax-h3 on Sume takes up to 9 reference images, 3 videos and 3 audios (12 total). The first 5 images cost nothing; each further image bills $0.10.
Written by Sume