generate_video
Transform text prompts into videos with customizable parameters like duration, resolution, and initial frame. Save outputs to specified directories using the MiniMax MCP JS server for AI-powered video generation.
Instructions
Generate a video based on text prompts.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
Input Schema
Name | Required | Description | Default |
---|---|---|---|
asyncMode | No | Whether to use async mode. Defaults to False. If True, the video generation task will be submitted asynchronously and the response will return a task_id. Should use `query_video_generation` tool to check the status of the task and get the result. | |
duration | No | The duration of the video. The model must be "MiniMax-Hailuo-02". Values can be 6 and 10. | |
firstFrameImage | No | First frame image | |
model | No | Model to use, values: ["T2V-01", "T2V-01-Director", "I2V-01", "I2V-01-Director", "I2V-01-live", "MiniMax-Hailuo-02"] | MiniMax-Hailuo-02 |
outputDirectory | No | The directory to save the output file. `outputDirectory` is relative to `MINIMAX_MCP_BASE_PATH` (or `basePath` in config). The final save path is `${basePath}/${outputDirectory}`. For example, if `MINIMAX_MCP_BASE_PATH=~/Desktop` and `outputDirectory=workspace`, the output will be saved to `~/Desktop/workspace/` | |
outputFile | No | Path to save the generated video file, automatically generated if not provided | |
prompt | Yes | Text prompt for video generation | |
resolution | No | The resolution of the video. The model must be "MiniMax-Hailuo-02". Values range ["768P", "1080P"] |