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

# Image To Audio

> Write a story about a local image with gpt-4o, then narrate it with gpt-audio and save the WAV to tmp/.

Image To Audio.

```python image_to_audio.py theme={null}
"""
Image To Audio
=============================

Image To Audio.
"""

from pathlib import Path

from agno.agent import Agent, RunOutput
from agno.media import Image
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file
from rich import print
from rich.text import Text

cwd = Path(__file__).parent.resolve()

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
image_agent = Agent(model=OpenAIChat(id="gpt-4o"))

image_path = Path(__file__).parent.joinpath("sample.jpg")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    image_story: RunOutput = image_agent.run(
        "Write a 3 sentence fiction story about the image",
        images=[Image(filepath=image_path)],
    )
    formatted_text = Text.from_markup(
        f":sparkles: [bold magenta]Story:[/bold magenta] {image_story.content} :sparkles:"
    )
    print(formatted_text)

    audio_agent = Agent(
        model=OpenAIChat(
            id="gpt-audio",
            modalities=["text", "audio"],
            audio={"voice": "sage", "format": "wav"},
        ),
    )

    audio_story: RunOutput = audio_agent.run(
        f"Narrate the story with flair: {image_story.content}"
    )
    if audio_story.response_audio is not None:
        write_audio_to_file(
            audio=audio_story.response_audio.content, filename="tmp/sample_story.wav"
        )
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```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"
      ```
    </CodeGroup>
  </Step>

  <Step title="Add the sample image">
    Place a JPEG named `sample.jpg` in the same directory as `image_to_audio.py`.
  </Step>

  <Step title="Run the example">
    Save the code above as `image_to_audio.py`, then run:

    ```bash theme={null}
    python image_to_audio.py
    ```
  </Step>
</Steps>

Full source: [cookbook/02\_agents/12\_multimodal/image\_to\_audio.py](https://github.com/agno-agi/agno/blob/main/cookbook/02_agents/12_multimodal/image_to_audio.py)