← All models
P Video Avatar
p-video-avatar generates talking-head videos from one portrait image plus a script or audio. 30 voices, 10 languages, 720p/1080p output. Run with an API.
Example
Details
- Accepts
- image + audio + video
Pricing
- Price
- 3.13 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed. Set for reproducible generation. |
| audio | string | Optional uploaded audio to drive avatar speech. If provided, this is used instead of voice_script and voice settings. |
| imagerequired | string | Input image (first frame). Supports jpg, jpeg, png, webp. |
| no_op | boolean | Health check mode - returns status without inference. |
| voice | —enum: Zephyr (Female), Puck (Male), Charon (Male), Kore (Female), Fenrir (Male), Leda (Female)… | Voice to use when generating speech from voice_script. |
| resolution | stringenum: 720p, 1080p | |
| video_prompt | string | Optional visual prompt describing how the person should appear or behave while speaking. |
| voice_prompt | string | Optional style instructions for how to speak voice_script, such as tone, pacing, accent, or emotion. These instructions are not spoken. |
| voice_script | string | Exact words the avatar should say. Required when no audio file is uploaded. |
| voice_language | —enum: English (US), English (UK), Spanish, French, German, Italian… | Language/accent target for generated speech. |
| negative_prompt | string | Disabled if empty.Mention what you do NOT want in the video, e.g. "subtitles, text, blurry, low quality, frames, watermark, titles, scene change". We recommend using multiple keywords at once. |
| disable_safety_filter | boolean | Disable safety filter for prompts and input image. When disabled, prompts are not checked for unsafe content before generation. |
| strength_negative_prompt | number | Strength of the Negative Prompt. Optimal value can differ for different video lengths (Experimental Feature) |
| disable_prompt_upsampling | boolean | When true, skip automatic enhancement of the visual video prompt and use video_prompt directly. |