# Audio Input Output (/examples/agents/multimodal/audio-input-output)



Audio Input Output.

```python title="audio_input_output.py"
"""
Audio Input Output
=============================

Audio Input Output.
"""

import requests
from agno.agent import Agent
from agno.media import Audio
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file
from rich.pretty import pprint

# Fetch the audio file and convert it to a base64 encoded string
url = "https://openaiassets.blob.core.windows.net/$web/API/docs/audio/alloy.wav"
response = requests.get(url)
response.raise_for_status()
wav_data = response.content

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIChat(
        id="gpt-audio",
        modalities=["text", "audio"],
        audio={"voice": "sage", "format": "wav"},
    ),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    run_response = agent.run(
        "What's in these recording?",
        audio=[Audio(content=wav_data, format="wav")],
    )

    if run_response.response_audio is not None:
        pprint(run_response.content)
        write_audio_to_file(
            audio=run_response.response_audio.content, filename="tmp/result.wav"
        )
```

<Note>
  OpenAI schedules `gpt-audio` for shutdown on January 20, 2027. It remains available until that announced date. See the [provider lifecycle notice](https://developers.openai.com/api/docs/deprecations) and verify audio formats and streaming support when selecting a replacement.
</Note>

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno openai requests
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```bash
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

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

    ```bash
    python audio_input_output.py
    ```
  </Step>
</Steps>

Full source: [cookbook/02\_agents/12\_multimodal/audio\_input\_output.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/02_agents/12_multimodal/audio_input_output.py)
