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

# Video generation

## Overview

Tool identifier `video_generate`.

`video_generate` generates videos from text. The example below first uses `image_generate` to create a first and last frame, then composes a video.

Import path: `from veadk.tools.builtin_tools.video_generate import video_generate`

## Environment & prerequisites

<Warning>
  Requirements:

  Configure an API key that can call the video-generation model. Set `MODEL_VIDEO_API_KEY` for a separate key; otherwise the tool uses `MODEL_AGENT_API_KEY`, then the Volcengine credentials available to the process. The example also calls `image_generate`, so the same credentials must be able to call the image model, or set `MODEL_IMAGE_API_KEY` separately.
</Warning>

Environment variables:

* `MODEL_VIDEO_API_KEY`: video-generation API key; defaults to the agent model credentials
* `MODEL_VIDEO_API_BASE`: video-generation endpoint; defaults to `https://ark.cn-beijing.volces.com/api/v3/`
* `MODEL_VIDEO_NAME`: video-generation model; defaults to `doubao-seedance-2-0-260128`
* `MODEL_IMAGE_API_KEY`: image-generation key used by the example; defaults to the agent model credentials
* `MODEL_IMAGE_NAME`: image-generation model used by the example; defaults to `doubao-seedream-5-0-260128`

`config.yaml` keys:

```yaml title="config.yaml" lines theme={null}
model:
  video:
    name: doubao-seedance-2-0-260128
    api_base: https://ark.cn-beijing.volces.com/api/v3/
    api_key: your-api-key-here
```

## Usage

```python title="examples/tools/video_generate/agent.py" lines theme={null}
import asyncio

from veadk import Agent, Runner
from veadk.memory.short_term_memory import ShortTermMemory
from veadk.tools.builtin_tools.image_generate import image_generate
from veadk.tools.builtin_tools.video_generate import video_generate

agent = Agent(
    name="video_generate_agent",
    model_name="doubao-seed-1-8-251228",
    description="An expert in creating images and videos.",
    instruction=(
        "First use image_generate to create a first frame and a last frame, then use "
        "video_generate to compose a video. Finally return the absolute path of the "
        "video and briefly summarize its content."
    ),
    tools=[image_generate, video_generate],
)

runner = Runner(agent=agent, short_term_memory=ShortTermMemory())


async def main():
    response = await runner.run(
        "Generate a puppy, then a scene of it flying into the sky, and finally compose a video"
    )
    print(response)


if __name__ == "__main__":
    asyncio.run(main())
```