> ## 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.

# Audio Input Agent

> Send an MP3 to gpt-audio through a local LiteLLM proxy with LiteLLMOpenAI.

Download an MP3 and pass it as audio input to a `gpt-audio` model served by a local LiteLLM proxy.

```python audio_input_agent.py theme={null}
"""
Please first install litellm[proxy] by running: uv pip install 'litellm[proxy]'

Before running this script, you need to start the LiteLLM server:

litellm --model gpt-audio --host 127.0.0.1 --port 4000
"""

import requests
from agno.agent import Agent, RunOutput  # noqa
from agno.media import Audio
from agno.models.litellm import LiteLLMOpenAI

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

# Fetch the QA audio file and convert it to a base64 encoded string
url = "https://agno-public.s3.us-east-1.amazonaws.com/demo_data/QA-01.mp3"
response = requests.get(url)
response.raise_for_status()
mp3_data = response.content

# Provide the agent with the audio file and get result as text
# Note: Audio input requires specific audio-enabled models like gpt-audio
agent = Agent(
    model=LiteLLMOpenAI(id="gpt-audio"),
    markdown=True,
)
agent.print_response(
    "What is in this audio?", audio=[Audio(content=mp3_data, format="mp3")], stream=True
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

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

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

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export LITELLM_API_KEY="your_litellm_api_key_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:LITELLM_API_KEY="your_litellm_api_key_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Start LiteLLM">
    Start the audio-capable local proxy on port 4000:

    ```bash theme={null}
    litellm --model gpt-audio --host 127.0.0.1 --port 4000
    ```
  </Step>

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

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

Full source: [cookbook/90\_models/litellm\_openai/audio\_input\_agent.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/litellm_openai/audio_input_agent.py)