← All modelsSoulX-FlashHead is a unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.
Example
Pricing
- Price
- 0.625 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|
| seed | — | Random seed for reproducibility. |
| textrequired | string | Text to speak. Converted to speech via ElevenLabs. |
| voice | stringenum: Aria, Roger, Sarah, Laura, Charlie, George… | ElevenLabs voice name. |
| image_urlrequired | string | URL of the face reference image. Portrait recommended. |
| stability | number | Voice stability (0-1). |
Output
| Field | Type | Description |
|---|
| seed | integer | The seed used for generation. |
| video | — | Generated lip-synced avatar video (512x512, 25 FPS). |
| timings | object | Timing breakdown. |
| duration | number | Video duration in seconds. |
