---
title: "p-video-avatar"
url: "https://docs.api.pruna.ai/apis/models-api-0/versions/783e153b-8e8d-4c8d-a80b-b80ec976bc53/schemas/p-video-avatar"
---

> Full API specification: https://docs.api.pruna.ai/apis/models-api-0/versions/783e153b-8e8d-4c8d-a80b-b80ec976bc53.md

# p-video-avatar

AI model for content generation. Rate limit: 50 requests per minute.

## OpenAPI definition

```yaml
openapi: 3.0.3
info:
  title: P-API
  version: 0.6.0
servers:
  - url: https://api.pruna.ai
    description: Production server
components:
  schemas:
    p-video-avatar:
      type: object
      required:
        - input
      properties:
        input:
          type: object
          properties:
            seed:
              title: Seed
              description: Random seed. Set for reproducible generation.
              type: integer
            audio:
              title: Audio
              format: uri
              description: Optional uploaded audio to drive avatar speech. If provided, this
                is used instead of voice_script and voice settings.
              type: string
            image:
              title: Image
              format: uri
              description: Input image (first frame). Supports jpg, jpeg, png, webp.
              type: string
            voice:
              enum:
                - Zephyr (Female)
                - Puck (Male)
                - Charon (Male)
                - Kore (Female)
                - Fenrir (Male)
                - Leda (Female)
                - Orus (Male)
                - Aoede (Female)
                - Callirrhoe (Female)
                - Autonoe (Female)
                - Enceladus (Male)
                - Iapetus (Male)
                - Umbriel (Male)
                - Algenib (Male)
                - Despina (Female)
                - Erinome (Female)
                - Laomedeia (Female)
                - Achernar (Female)
                - Algieba (Male)
                - Schedar (Male)
                - Gacrux (Female)
                - Pulcherrima (Female)
                - Achird (Male)
                - Zubenelgenubi (Male)
                - Vindemiatrix (Female)
                - Sadachbia (Male)
                - Sadaltager (Male)
                - Sulafat (Female)
                - Alnilam (Male)
                - Rasalgethi (Male)
              title: voice
              description: Voice to use when generating speech from voice_script.
              default: Zephyr (Female)
              type: string
            resolution:
              enum:
                - 720p
                - 1080p
              title: resolution
              description: Resolution of the video.
              default: 720p
              type: string
            video_prompt:
              title: Video Prompt
              default: The person is talking.
              description: Optional visual prompt describing how the person should appear or
                behave while speaking.
              type: string
            voice_prompt:
              title: Voice Prompt
              default: Say the following.
              description: Optional style instructions for how to speak voice_script, such as
                tone, pacing, accent, or emotion. These instructions are not
                spoken.
              type: string
            voice_script:
              title: Voice Script
              default: ""
              description: Exact words the avatar should say. Required when no audio file is
                uploaded.
              type: string
            voice_language:
              enum:
                - English (US)
                - English (UK)
                - Spanish
                - French
                - German
                - Italian
                - Portuguese (Brazil)
                - Japanese
                - Korean
                - Hindi
              title: voice_language
              description: Language/accent target for generated speech.
              default: English (US)
              type: string
            negative_prompt:
              title: Negative Prompt
              default: ""
              description: 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.
              type: string
            disable_safety_filter:
              title: Disable Safety Filter
              default: true
              description: Disable safety filter for prompts and input image. When disabled,
                prompts are not checked for unsafe content before generation.
              type: boolean
            strength_negative_prompt:
              title: Strength Negative Prompt
              default: 0.5
              maximum: 4
              minimum: 0
              description: Strength of the Negative Prompt. Optimal value can differ for
                different video lengths (Experimental Feature)
              type: number
            disable_prompt_upsampling:
              title: Disable Prompt Upsampling
              default: false
              description: When true, skip automatic enhancement of the visual video prompt
                and use video_prompt directly.
              type: boolean
          required:
            - image
          additionalProperties: false
      description: "AI model for content generation. Rate limit: 50 requests per minute."
```