ComfyUI Node
Superside MiniMax H3 Max Lip Sync
MiniMax H3 Max Lip Sync on fal. Returns a native VIDEO plus the URL, so SaveVideo or PreviewVideo connects straight in. Endpoint: default - minimax/h3-max/lip-sync/image-to-video fal price (2026-10-30): Billing is calculated per second of generated video. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. A 1.2x multiplier is added to videos over 15 seconds. A 5-second video at 768p costs $0.40.
Superside MiniMax H3 Max Lip Sync
- image_url
- video
- video_url
◄audio_url►
◄api_key►
◄seed0►
◄enable_safety_checkertrue►
◄resolution768P►
◄enable_transcriptionfalse►
CategorySuperside
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| audio_url | STRING | Audio to synchronize the mouth movements to, at least 5 seconds long. Supports up to 15 minutes. The output video matches the supplied audio duration. | |
| image_url | IMAGE | Image to animate. The aspect ratio must be between 0.4 and 2.5. | |
| api_key | STRING | — | |
| seedopt | INT | 0-1–2147483647 | Random seed; selected randomly if omitted. -1 = let the model choose. |
| enable_safety_checkeropt | BOOLEAN | true | Enable content safety checks. |
| resolutionopt | COMBO | 768P | Output resolution. Uses the supported aspect ratio nearest the image. |
| enable_transcriptionopt | BOOLEAN | false | Transcribe the supplied audio to guide lip synchronization. When disabled, synchronize to the audio without a transcript. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| video_url | STRING | — |