Audio
Room tone vs performance voice on spicy MiniMax H3
MiniMax H3 already makes room tone: rain, cloth, a mattress, a distant corridor. That is native audio, generated with the picture. A whisper, a short line, a language swap, a voice you own — that is a performance pass. Mixing both into one 8s text-to-video prompt is how you get a mouth that chews the rain.
The native-audio craft is on native audio on MiniMax H3 clips. This note is the spicy split: what belongs in the H3 take, and what belongs on spicy audio or lip-sync.
Leave in the H3 take
- Weather and surfaces — rain on glass, tyres, cloth on sheets.
- One bed. Not a score plus a voiceover plus three foley layers.
- Breath as atmosphere, not as a speech performance.
Second pass
- Your voice — a recording you have the right to use. Not a celebrity. Not a stranger. Cloning real people is not offered.
- Translate + lip-sync — keep the performance, change the language.
- A short line — “slow”, “look at me”. Short mouths are H3-friendly; paragraphs are not.
- Phone-call framing — picture on the listener; the other voice is off-screen.
H3 tiers and list prices, for the picture pass:
| H3 tier | per second | resolution | duration |
|---|---|---|---|
| MiniMax H3-Developer Text-to-Video | $0.030 | 480P, 768P, 1440p-sr, 4k-sr | 4–15s |
| MiniMax H3-Developer Image-to-Video | $0.030 | 480P, 768P, 1440p-sr, 4k-sr | 4–15s |
| MiniMax H3-Developer Reference-to-Video | $0.030 | 480P, 768P, 1440p-sr, 4k-sr | 4–15s |
| MiniMax H3 Max Turbo Text-to-Video | $0.036 | 480P, 768P | 5–15s |
| MiniMax H3 Max Turbo Image-to-Video | $0.036 | 480P, 768P | 5–15s |
| MiniMax H3 Text-to-Video | $0.057 | 480P, 768P, 2K | 4–15s |
| MiniMax H3 Image-to-Video | $0.057 | 480P, 768P, 2K | 4–15s |
| MiniMax H3 Reference-to-Video | $0.057 | 480P, 768P, 2K | 4–15s |
| MiniMax H3 Fast Text-to-Video | $0.066 | 480P | 5–15s |
| MiniMax H3 Fast Image-to-Video | $0.066 | 480P | 5–15s |
| MiniMax H3 Fast Reference-to-Video | $0.066 | 480P | 5–15s |
| MiniMax H3 Max Text-to-Video | $0.072 | 480P, 768P, 1440p-sr, 4k-sr | 5–15s |
| MiniMax H3 Max Image-to-Video | $0.072 | 480P, 768P, 1440p-sr, 4k-sr | 5–15s |
Across the 203 video models on this site the per-second list price runs from $0.0030 to $0.73 — a spread of roughly 245× between the cheapest and the dearest. The H3 family sits inside that range at $0.030–$0.072 per second.
Do not pay a Max render to also act as a voice actor. Print the picture, then run audio. Invite or waitlist; billing is not live.