> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# YouTube Tools

> Fetch YouTube video captions and answer questions about the video with YouTubeTools.

```python youtube_tools.py theme={null}
"""
Youtube Tools
=============================

Demonstrates youtube tools.
"""

from agno.agent import Agent
from agno.tools.youtube import YouTubeTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


agent = Agent(
    tools=[YouTubeTools()],
    description="You are a YouTube agent. Obtain the captions of a YouTube video and answer questions.",
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "Summarize this video https://www.youtube.com/watch?v=Iv9dewmcFbs&t",
        markdown=True,
    )
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno openai youtube-transcript-api
```

**2. Export your OpenAI API key**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

Save the code above as `youtube_tools.py`, then run:

```bash theme={null}
python youtube_tools.py
```

Full source: [cookbook/91\_tools/youtube\_tools.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/91_tools/youtube_tools.py)


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