---
title: P-Video-Avatar | Runware Docs
url: https://runware.ai/docs/models/prunaai-p-video-avatar
description: High-fidelity talking avatar video generation from a portrait with script or audio control
---
# P-Video-Avatar

![P-Video-Avatar](https://assets.runware.ai/covers/prunaai-p-video-avatar.jpg)

P-Video-Avatar is a portrait-driven avatar video model that turns a single image into a speaking video using either an uploaded audio track or a generated voice from script. It is built for production avatar workflows with strong lip sync, selectable voices and languages, optional speaking-style control, seeded generation, and 720p or 1080p output for scalable talking-head video creation.

- **Status**: live
- **ID**: `prunaai:p-video@avatar`
- Try in Playground
- **Creator**: Pruna AI
- **Release Date**: April 30, 2026
- **Capabilities**: Image to Video, Audio to Video, Checkpoint, Audio

## Pricing

$0.025 from, per second · ~1m 5s per request

**Rates** (per second)

- 720p: `$0.025`
- 1080p: `$0.045`

**4 example generations**

- [scripted-photo-avatar](https://runware.ai/docs/models/prunaai-p-video-avatar/examples#example-indigo-dyehouse-music-video-bridge) · 720p: `$0.219` (~26s)
- [scripted-photo-avatar](https://runware.ai/docs/models/prunaai-p-video-avatar/examples#example-airport-biosecurity-training-presenter) · 720p: `$0.423` (~4m 8s)
- [audio-driven-photo-avatar](https://runware.ai/docs/models/prunaai-p-video-avatar/examples#example-prestige-fragrance-mystery-teaser) · 1080p: `$0.488` (~1m 5s)
- [audio-driven-photo-avatar](https://runware.ai/docs/models/prunaai-p-video-avatar/examples#example-seed-vault-thriller-teaser) · 1080p: `$0.50` (~1m 6s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Provide exactly one of: `inputs.audio`, `speech.text`.

---

When `resolution` is provided, `inputs.frameImages` is required.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/prunaai-p-video-avatar#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/prunaai-p-video-avatar#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/prunaai-p-video-avatar#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/prunaai-p-video-avatar#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/prunaai-p-video-avatar#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/prunaai-p-video-avatar#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/prunaai-p-video-avatar#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/prunaai-p-video-avatar#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/prunaai-p-video-avatar#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/prunaai-p-video-avatar#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/prunaai-p-video-avatar#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/prunaai-p-video-avatar#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/prunaai-p-video-avatar#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/prunaai-p-video-avatar#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [frameImages](https://runware.ai/docs/models/prunaai-p-video-avatar#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Required**: true
- **Min items**: `items: 1`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/prunaai-p-video-avatar#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/prunaai-p-video-avatar#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. This model only supports the first frame.

**Allowed values**:

- `first` First frame of the video.
- `0` Frame index 0 (first frame).

### [audio](https://runware.ai/docs/models/prunaai-p-video-avatar#request-inputs-audio)

- **Path**: `inputs.audio`
- **Type**: `string`

Audio input (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/prunaai-p-video-avatar#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `prunaai:p-video@avatar`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/prunaai-p-video-avatar#request-positiveprompt)

- **Type**: `string`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [resolution](https://runware.ai/docs/models/prunaai-p-video-avatar#request-resolution)

- **Type**: `string`
- **Default**: `720p`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `720p` `1080p`

### [seed](https://runware.ai/docs/models/prunaai-p-video-avatar#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

### [speech](https://runware.ai/docs/models/prunaai-p-video-avatar#request-speech)

- **Path**: `speech.text`
- **Type**: `object (3 properties)`

Settings for speech generation.

#### [text](https://runware.ai/docs/models/prunaai-p-video-avatar#request-speech-text)

- **Path**: `speech.text`
- **Type**: `string`
- **Min**: `1`
- **Max**: `5000`

Text to convert to speech.

#### [voice](https://runware.ai/docs/models/prunaai-p-video-avatar#request-speech-voice)

- **Path**: `speech.voice`
- **Type**: `string`
- **Default**: `Zephyr (Female)`

Voice identifier to use for speech generation.

**Allowed values**: `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)`

#### [language](https://runware.ai/docs/models/prunaai-p-video-avatar#request-speech-language)

- **Path**: `speech.language`
- **Type**: `string`
- **Min**: `1`
- **Default**: `en-US`

Language code for speech generation.

**Allowed values**: `en` `en-US` `en-GB` `es` `es-ES` `fr` `fr-FR` `de` `de-DE` `it` `it-IT` `pt-BR` `ja` `ja-JP` `ko` `ko-KR` `hi` `hi-IN`

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [promptUpsampling](https://runware.ai/docs/models/prunaai-p-video-avatar#request-settings-promptupsampling)

- **Path**: `settings.promptUpsampling`
- **Type**: `boolean`
- **Default**: `false`

Automatically enhance the prompt for improved results.

### [safetyFilter](https://runware.ai/docs/models/prunaai-p-video-avatar#request-settings-safetyfilter)

- **Path**: `settings.safetyFilter`
- **Type**: `boolean`
- **Default**: `true`

Content safety filtering. Applies to prompts and the input image.

### [voicePrompt](https://runware.ai/docs/models/prunaai-p-video-avatar#request-settings-voiceprompt)

- **Path**: `settings.voicePrompt`
- **Type**: `string`
- **Default**: `Say the following.`

Speaking style, tone, pacing, or emotion instructions for delivery.

## Response Parameters

### [taskType](https://runware.ai/docs/models/prunaai-p-video-avatar#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/prunaai-p-video-avatar#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/prunaai-p-video-avatar#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/prunaai-p-video-avatar#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/prunaai-p-video-avatar#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/prunaai-p-video-avatar#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/prunaai-p-video-avatar#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/prunaai-p-video-avatar#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/prunaai-p-video-avatar#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### audio-driven-photo-avatar (audio-driven-photo-avatar)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-avatar/96a60538-e96f-4d69-a912-d61d3f85728a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "5fabd35e-09d5-4168-85c2-df83cf2b30cd",
  "model": "prunaai:p-video@avatar",
  "positivePrompt": "Animate this portrait as the ominous cold open of a prestige agricultural conspiracy thriller. The plant pathologist speaks directly to camera with precise lip synchronization, controlled urgency, and quiet dread. Preserve her identity, saffron coverall, Arctic seed-vault corridor, natural polar daylight, and centered front-facing composition. Use subtle facial tension, a slight tightening around the eyes, natural blinking, gentle breathing, and very restrained head movement. Keep the camera locked and the background stable. Photorealistic cinematic performance with no exaggerated gestures, no added people, no titles, and no on-screen text.",
  "resolution": "1080p",
  "speech": {
    "voice": "Aoede (Female)"
  },
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/8ed7eabe-7f1b-4336-b787-754c7e2ec7f2.jpg"
    ],
    "audio": "https://assets.runware.ai/assets/inputs/9a2c7321-0dd3-4d86-8859-e5dc67ca779b.mp3"
  }
}
```

---

### scripted-photo-avatar (scripted-photo-avatar)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-avatar/25d0f697-ae15-4224-8bad-b9134fd7b524.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "9e334a80-a5cb-4965-a56e-410508f7354f",
  "model": "prunaai:p-video@avatar",
  "positivePrompt": "Create an intimate spoken-word music-video performance from this portrait. The vocalist looks directly into the lens and delivers the Spanish lyric with precise, natural lip synchronization. Include realistic blinking, a soft inhale before speaking, restrained facial emotion that develops from reflection into quiet resolve, and subtle organic head movement. Keep her shoulders composed and avoid exaggerated gestures. Preserve the cobalt, ochre, and ivory dyehouse palette, soft natural window light, shallow depth of field, and understated analog-film texture. Locked eye-level camera, polished cinematic realism, no captions or on-screen text.",
  "resolution": "720p",
  "speech": {
    "text": "Guardo el azul en las manos; no por tristeza, sino para recordar que hasta la noche aprende a cambiar.",
    "voice": "Aoede (Female)",
    "language": "es"
  },
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/c7a9a08e-58c4-48aa-875b-1b9f19256f4f.jpg"
    ]
  }
}
```

---

### scripted-photo-avatar (scripted-photo-avatar)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-avatar/df661443-90a6-4c1e-a2f2-b48ea175f1f0.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "e5eddb14-70c1-43df-a72b-b92d03c01187",
  "model": "prunaai:p-video@avatar",
  "positivePrompt": "Create a polished airport biosecurity microlearning presenter clip from the supplied portrait. The entomologist speaks directly to the viewer with precise natural lip synchronization, steady eye contact, occasional realistic blinking, subtle head movement, and a calm but appropriately vigilant facial expression. Preserve her identity, clothing, inspection-room setting, natural skin texture, and soft documentary lighting. Keep the camera locked in a stable front-facing medium close-up with no cuts, reframing, gestures entering the frame, background distractions, captions, logos, or on-screen text.",
  "resolution": "720p",
  "speech": {
    "text": "If you spot a gray, putty-like egg mass on outdoor luggage, don't scrape it off. Place the item in the inspection tray, note its origin, and call the biosecurity desk. One careful pause can keep an invasive pest from crossing the border.",
    "voice": "Kore (Female)",
    "language": "en-US"
  },
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/7d422411-ed05-4953-bc10-5643e01b6bf7.jpg"
    ]
  }
}
```

---

### audio-driven-photo-avatar (audio-driven-photo-avatar)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-avatar/9363f2ef-e3c6-4ba4-b25a-2cfecd68c804.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "36724d89-ec76-4dc7-9c35-8811b4c7f1dc",
  "model": "prunaai:p-video@avatar",
  "positivePrompt": "Create a cinematic prestige-mystery teaser from the supplied portrait and clean dialogue. Preserve the forensic perfumer's identity, wardrobe, centered chest-up framing, natural window light, shallow depth of field, and celadon-charcoal-amber color grade. She addresses the viewer with controlled authority and a trace of unease, maintaining direct eye contact. Use precise lip synchronization throughout, subtle facial tension, natural blinking, a slight measured inhale, and restrained head movement. Her expression should sharpen almost imperceptibly on the final phrase. Keep the shot continuous and composed, with no camera movement, cuts, additional people, added objects, or on-screen text.",
  "resolution": "1080p",
  "speech": {
    "voice": "Algieba (Male)"
  },
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/bb7f5ad4-5c5b-4d4e-ad99-5647bb8eaaa1.jpg"
    ],
    "audio": "https://assets.runware.ai/assets/inputs/f43bee72-d64c-4ca1-a57f-0d5a5a6ce6ed.mp3"
  }
}
```