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

# Process Video • AI Agent SDK

> process_video: Split video into frames (base64-encoded).

# process\_video

<div className="flex items-center gap-2">
  <Badge color="teal">Function</Badge>
</div>

> This function is defined in the [**agents**](../modules/agents) module.

Split video into frames (base64-encoded).

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def process_video(video_path: str, seconds_per_frame: Any) -> Any
```

## Parameters

<ParamField query="video_path" type="str" required={true}>
  No description available.
</ParamField>

<ParamField query="seconds_per_frame" type="Any" required={false} default="2">
  No description available.
</ParamField>

### Returns

<ResponseField name="Returns" type="Any">
  The result of the operation.
</ResponseField>

## Uses

* `cv2.VideoCapture`
* `video.read`
* `cv2.imencode`
* `decode`
* `base64.b64encode`
* `video.release`

## Used By

* [`get_multimodal_message`](../functions/get_multimodal_message)

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/agents/agents.py#L44">
  `praisonaiagents/agents/agents.py` at line 44
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Multimodal" icon="video" href="/docs/features/multimodal" />
</CardGroup>