← All models
MultiTalk model generates a talking avatar video from an image and text. Converts text to speech automatically, then generates the avatar speaking with lip-sync.
Example
Details
- Accepts
- image
Pricing
- Price
- 25 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed for reproducibility. If None, a random seed is chosen. |
| voicerequired | stringenum: Aria, Roger, Sarah, Laura, Charlie, George… | The voice to use for speech generation |
| promptrequired | string | The text prompt to guide video generation. |
| image_urlrequired | string | URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped. |
| num_frames | integer | Number of frames to generate. Must be between 41 to 721. |
| resolution | stringenum: 480p, 720p | Resolution of the video to generate. Must be either 480p or 720p. |
| text_inputrequired | string | The text input to guide video generation. |
| acceleration | stringenum: none, regular, high | The acceleration level to use for generation. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for generation. |
| video | — | The generated video file. |