> ## Documentation Index
> Fetch the complete documentation index at: https://docs.argil.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pi Video

> Generate a video with PrunaAI Pi Video from text, from an image, or from an image synced to an audio track. Up to 10 s (audio: its length), 720p or 1080p, draft mode for cheap previews.

Model id `pi-video` · Pi Labs · video · 3 modes: `text-to-video`, `image-to-video`, `audio-to-video`.

> [!NOTE]
>
> This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls [`get_model`](https://docs.argil.ai/v2/mcp/tools) with the mode.

## Text To Video

Mode `text-to-video`. Text to video. Enabled on request.

### Input

| Field | Type | Required | Allowed | Default | Description |
| - | - | - | - | - | - |
| `prompt` | string | Yes | | | What the video should show: subject, action, camera and style. |
| `duration` | integer | | 1 to 10 | | Video duration in seconds, 1-10 (default 5). |
| `aspect_ratio` | string | | `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `1:1` | | Aspect ratio of the video (default 16:9). |
| `resolution` | string | | `720p`, `1080p` | | Output resolution (default 720p). |
| `fps` | integer | | `24`, `48` | | Frames per second: 24 (default) or 48. |
| `draft` | boolean | | | | Draft mode: faster, cheaper, lower-quality previews. |
| `seed` | integer | | | | Seed. Random when omitted. |
| `prompt_upsampling` | boolean | | | | Enhance the prompt before generating (default true). |

### Pricing

0.97 credits/s (720p), 1.94 credits/s (1080p), draft: 0.24 credits/s (720p), 0.48 credits/s (1080p), per second of output video (audio-to-video: the audio's length); settled on the seconds Replicate bills.

Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded.

For the exact price of a request, use [`estimate_generation`](https://docs.argil.ai/v2/mcp/tools).

### Example

The arguments of [`generate_media`](https://docs.argil.ai/v2/mcp/tools#generate_media):

```json theme={null}
{
  "model": "pi-video",
  "mode": "text-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera",
    "duration": 1,
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}
```

## Image To Video

Mode `image-to-video`. Animate an image. Enabled on request.

### Input

| Field | Type | Required | Allowed | Default | Description |
| - | - | - | - | - | - |
| `prompt` | string | Yes | | | What the video should show: subject, action, camera and style. |
| `duration` | integer | | 1 to 10 | | Video duration in seconds, 1-10 (default 5). |
| `resolution` | string | | `720p`, `1080p` | | Output resolution (default 720p). |
| `fps` | integer | | `24`, `48` | | Frames per second: 24 (default) or 48. |
| `draft` | boolean | | | | Draft mode: faster, cheaper, lower-quality previews. |
| `seed` | integer | | | | Seed. Random when omitted. |
| `prompt_upsampling` | boolean | | | | Enhance the prompt before generating (default true). |
| `first_frame` | [File](https://docs.argil.ai/v2/mcp/how-it-works.md#your-files) | Yes | | | The image to animate, as the first frame. |

### Pricing

0.97 credits/s (720p), 1.94 credits/s (1080p), draft: 0.24 credits/s (720p), 0.48 credits/s (1080p), per second of output video (audio-to-video: the audio's length); settled on the seconds Replicate bills.

Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded.

For the exact price of a request, use [`estimate_generation`](https://docs.argil.ai/v2/mcp/tools).

### Example

The arguments of [`generate_media`](https://docs.argil.ai/v2/mcp/tools#generate_media):

```json theme={null}
{
  "model": "pi-video",
  "mode": "image-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera",
    "duration": 1,
    "resolution": "720p",
    "first_frame": "asset_91a3c7e5b2d84f6a8e0c1b9d7f3a5e24"
  }
}
```

## Audio To Video

Mode `audio-to-video`. Animate an image, synced to an audio track. Enabled on request.

### Input

| Field | Type | Required | Allowed | Default | Description |
| - | - | - | - | - | - |
| `prompt` | string | Yes | | | What the video should show: subject, action, camera and style. |
| `resolution` | string | | `720p`, `1080p` | | Output resolution (default 720p). |
| `fps` | integer | | `24`, `48` | | Frames per second: 24 (default) or 48. |
| `draft` | boolean | | | | Draft mode: faster, cheaper, lower-quality previews. |
| `seed` | integer | | | | Seed. Random when omitted. |
| `prompt_upsampling` | boolean | | | | Enhance the prompt before generating (default true). |
| `first_frame` | [File](https://docs.argil.ai/v2/mcp/how-it-works.md#your-files) | Yes | | | The image to animate, as the first frame. |
| `reference_audio` | [File](https://docs.argil.ai/v2/mcp/how-it-works.md#your-files) | Yes | | | The audio driving the video; the video matches its length. |

### Pricing

0.97 credits/s (720p), 1.94 credits/s (1080p), draft: 0.24 credits/s (720p), 0.48 credits/s (1080p), per second of output video (audio-to-video: the audio's length); settled on the seconds Replicate bills.

Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded.

For the exact price of a request, use [`estimate_generation`](https://docs.argil.ai/v2/mcp/tools).

### Example

The arguments of [`generate_media`](https://docs.argil.ai/v2/mcp/tools#generate_media):

```json theme={null}
{
  "model": "pi-video",
  "mode": "audio-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera",
    "resolution": "720p",
    "first_frame": "asset_91a3c7e5b2d84f6a8e0c1b9d7f3a5e24",
    "reference_audio": "asset_5d2b8f0e6c3a4d9b8e1f7a2c4b6d8e03"
  }
}
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.