> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Multi-turn Audio Agent

## Code

```python theme={null}
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file

agent = Agent(
    model=OpenAIChat(
        id="gpt-4o-audio-preview",
        modalities=["text", "audio"],
        audio={"voice": "alloy", "format": "wav"},
    ),
    debug_mode=True,
    add_history_to_messages=True,
)

agent.run("Is a golden retriever a good family dog?")
if agent.run_response.response_audio is not None:
    write_audio_to_file(
        audio=agent.run_response.response_audio.content, filename="tmp/answer_1.wav"
    )

agent.run("Why do you say they are loyal?")
if agent.run_response.response_audio is not None:
    write_audio_to_file(
        audio=agent.run_response.response_audio.content, filename="tmp/answer_2.wav"
    )
```

## Usage

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

**1. Set your API key**

```bash theme={null}
export OPENAI_API_KEY=xxx
```

**2. Install libraries**

```bash theme={null}
pip install -U openai agno
```

**3. Run Agent**

```bash Mac theme={null}
python cookbook/agent_concepts/multimodal/audio_multi_turn.py
```

```bash Windows theme={null}
python cookbook/agent_concepts/multimodal/audio_multi_turn.py
```


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