MiniMax H3 clip audio: keep it or detach it for a Short
MiniMax H3 is reported to make native stereo audio. Detach it for $0.01 to mix it separately. Prices for H3 768p and H3 Max.
The magichour.ai release tracker (read 2026-10-07) reports MiniMax H3 with native stereo audio. For a Short with a separate voice and bed, the clip's own sound is either a bonus or a clash.
Sume lists H3 and H3 Max. Per the repo's estimator, an 8-second 768p clip is $0.60 on H3 and $0.80 on H3 Max.
Keep or detach
| Job | Choice | Extra cost |
|---|---|---|
| Ambient sound fits the scene | Keep, add a quiet bed | $0 |
| You are adding a voiceover | Detach, then mix or drop | $0.01 |
| Need only the sound design | Detach as wav or mp3 | $0.01 |
Detach details
Audio detach is a flat $0.01 per job, takes a source up to 1800 seconds, and returns wav or mp3 up to 900 seconds. Muting in your editor is free if you already have one. Detach is useful when you want the sound as a file to level against the voice.
With H3 at $0.60 plus detach at $0.01, the clip and its sound file cost $0.61 together.
Sources
Related posts
More in Models
- Minimum clip length by Sume video model: 2, 3, 4 or 5 seconds
Wan 3.0 starts at 2 s, Gemini Omni Flash 1.1 at 3 s, Seedance and Genjutsu at 4 s, MiniMax H3 and Recast at 5 s. Full min and max table for a Sora port.
- Music Router image_url: public HTTPS only, and null to clear it
Sume music image_url must be a public HTTPS image, and null clears it on a reused request object. When a mood still helps and when the prompt does more.
- Nano Banana 2.1 has no 512px size in Google's guide; Sume lists 512
Google's guide says 512px is unsupported on Nano Banana 2.1, yet Sume's catalog enum for it starts at 512. How to test what a call returns.
- Nano Banana 2.1 tracks 4 characters, 10 objects: Sume's cap
Google says Nano Banana 2.1 tracks 4 characters and 10 objects across up to 14 references. Sume's Image API caps input_references at 10, or 16 on GPT.
Written by Sume