---
title: "P-Video-Avatar"
description: "Turn one portrait and an English script into a speaking video in the 720p tier. The model determines the video dimensions and length."
seo:
  title: "P-Video-Avatar API Documentation: Parameters & Examples"
  description: "P-Video-Avatar API documentation: model ID pruna/p-video-avatar, input modes, parameters, defaults and request examples. Turn one portrait and an English script into a speaking video in the 720p tier. The model determines the video dimensions and length."
---

{/* Generated by scripts/generate-model-pages.mjs from openapi/model-contracts.json. Do not edit; write notes in docs/models/_notes/pruna/p-video-avatar.mdx */}

| Model ID | Alias | Endpoint |
| --- | --- | --- |
| `pruna/p-video-avatar` | `p-video-avatar` | [Video generation](/docs/guides/video-generation) |

## Input modes

| Mode | References | Reference roles |
| --- | --- | --- |
| `reference` Reference media | 1 | `reference_image` |

## Parameters

| Parameter | Description | Values | Default | Required |
| --- | --- | --- | --- | --- |
| `resolution` | Resolution: Output resolution. | `720p` | `720p` | No |
| `aspect_ratio` | Aspect ratio: Output aspect ratio. | `auto` | `auto` | No |
| `n` | Outputs per request: Number of outputs from one API request (one Job), not the application batch size. For multiple Jobs, submit separate requests; n=1 does not prevent application-managed batching. | `1` | `1` | No |

## Examples

`reference` input:

```json
{
  "model": "pruna/p-video-avatar",
  "input": {
    "type": "reference",
    "prompt": "Welcome to the team. Here is what to expect on your first day.",
    "references": [
      {
        "role": "reference_image",
        "file_id": "file_..."
      }
    ]
  },
  "parameters": {
    "resolution": "720p",
    "aspect_ratio": "auto",
    "n": 1
  }
}
```

The authoritative contract is `GET /v1/models/pruna/p-video-avatar?view=contract`. A valid parameter does not mean every channel can run it, so [quote](/docs/concepts/billing#get-a-quote) the complete request. Prices and channels are listed in [Model Market](https://yir.ai/models).

Send one portrait as `reference_image` and the English words to speak as `input.prompt`. The model uses the fixed Zephyr voice and returns a speaking MP4 in the 720p tier. The model determines the exact dimensions and duration.

The listed rate is $0.025 per output second. The API settles the task after rendering using the upstream charge for that task. Leave out `duration` and `generate_audio`. The final total is unavailable before rendering, so requests with `max_cost` are unavailable on this route.
