# MiniMax H3 Max Lip Sync

This node animates a still image so that the mouth movements follow a supplied audio track. The image and audio are uploaded, the Hailuo 03 Max lip-sync job is polled, and the talking video comes back at the resolution you choose. The output video is as long as the audio.

## Inputs

### Common Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `model` | Model to use for video generation. | DYNAMIC_COMBO | Yes | "MiniMax H3 Max" |

### MiniMax H3 Max Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `image` | Image to animate, at least 256x256 pixels. The aspect ratio must be between 0.4 and 2.5. | IMAGE | Yes | Single image |
| `audio` | Audio to lip-sync to, 5 to 899 seconds long. | AUDIO | Yes | 5 to 899 seconds |
| `resolution` | Output resolution (default: "768P"). The aspect ratio is the supported one nearest to the image. | COMBO | Yes | "480P"<br>"768P"<br>"1080P"<br>"2K" |
| `transcription` | Transcribe the audio to guide the lip synchronization (default: false). | BOOLEAN | No | true<br>false |
| `seed` | Random seed. The same request with the same seed gives similar, but not guaranteed identical, results (default: 42). | INT | Yes | 0 to 2147483647 |

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `video` | The talking video, as long as the input audio. | VIDEO |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxHailuo03MaxLipSyncNode/en.md)

---
**Source fingerprint (SHA-256):** `0af4166f9f3237cacc3506d6c6544c0374a330cf998f8bd2ef1f4f7162e2f9ab`
