← All models
Omnihuman v2 generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.
Example
Details
- Accepts
- text
Pricing
- Price
- 13.13 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| prompt | — | Optional text prompt for precise control of the scene, movements and camera. Supported languages: Chinese, English, Japanese, Korean, Spanish (Mexican) and Indonesian. |
| audio_urlrequired | string | The URL of the audio file to generate the video. Format: wav or mp3. Max size: 15 MB. Duration between 4 and 300 seconds. |
| image_urlrequired | string | The URL of the image used to generate the video. Format: jpeg, png, webp, bmp, tiff, gif, heic or heif. Max size: 30 MB. Aspect ratio (width/height) between 0.4 and 2.5; width and height between 300 and 6000 pixels. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | Generated video file |
| duration | number | Duration of audio input/video output as used for billing. |