← All models
Audio-driven talking avatar generation powered by the SoulX-FlashTalk 14B model.
Details
- Accepts
- image + audio
Pricing
- Price
- 2.5 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. |
| audio_urlrequired | string | URL of the speech audio file (WAV, MP3, etc). |
| image_urlrequired | string | URL of the face reference image. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for generation. |
| video | — | Generated lip-synced avatar video (768x448, 25 FPS). |
| timings | object | Timing breakdown. |
| duration | number | Video duration in seconds. |