← All models
H3 Max Lip Sync generates a video from an image and supplied audio, synchronizing mouth movements to the soundtrack. It supports optional transcription guidance and output resolutions from 480p to 2K.
Example
Details
- Accepts
- image + audio
Pricing
- Price
- 6.25 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed; selected randomly if omitted. |
| audio_urlrequired | 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_urlrequired | string | Image to animate. The aspect ratio must be between 0.4 and 2.5. |
| resolution | stringenum: 480P, 768P, 1080P, 2K | Output resolution. Uses the supported aspect ratio nearest the image. |
| enable_transcription | boolean | Transcribe the supplied audio to guide lip synchronization. When disabled, synchronize to the audio without a transcript. |
| enable_safety_checker | boolean | Enable content safety checks. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed used for generation. |
| video | — | Lip-synced video with the supplied soundtrack. |
| timings | — | Timing breakdown in seconds. 'inference' is the DiT denoising time on the GPU backend, summed over every window this request generated. Null on routes that do not report backend timings. |
| duration | number | Output duration in seconds. |