# MiniMax H3 Recast (https://docs.fuser.studio/docs/nodes/video/minimax-h3-recast)

_Provided by [Fal](https://fal.ai) — [Learn More](https://fal.ai/models/minimax/h3-max/recast)._

Model page: https://fuser.studio/models/minimax-h3-recast

## Inputs [#inputs]

- **Video** (`video`) — The source video, 5 to 30 seconds long, with no single shot longer than 15 seconds. Its sound is kept.

   Optional: `true`

- **People** (`image`) _(accepts multiple)_ — One photo per new person, up to 4. By default they replace the main people in the video from left to right.

   Optional: `true`

- **Prompt** (`textarea`) — Optional: who becomes whom, or what else to keep or change.

   Optional: `true`

- **Resolution** (`dropdown`) — Output resolution. The recast video keeps the length of the source video.

   Optional: `true` • Default: `1080P` • Accepts: `768p`, `1080p`

## Outputs [#outputs]

- **Recast Video** (`video`) — The recast video, with the source sound.