> ## 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.

# Audio Output Agent

> Get text and spoken audio from gpt-audio and save the responses to WAV files.

## Code

```python audio_output_agent.py theme={null}
from agno.agent import Agent, RunOutput  # noqa
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file
from agno.db.in_memory import InMemoryDb

# Provide the agent with the audio file and audio configuration and get result as text + audio
agent = Agent(
    model=OpenAIChat(
        id="gpt-audio",
        modalities=["text", "audio"],
        audio={"voice": "sage", "format": "wav"},
    ),
    db=InMemoryDb(),
    add_history_to_context=True,
    markdown=True,
)
run_output: RunOutput = agent.run("Tell me a 5 second scary story")

# Save the response audio to a file
if run_output.response_audio:
    write_audio_to_file(
        audio=run_output.response_audio.content, filename="tmp/scary_story.wav"
    )

run_output: RunOutput = agent.run("What would be in a sequel of this story?")

# Save the response audio to a file
if run_output.response_audio:
    write_audio_to_file(
        audio=run_output.response_audio.content,
        filename="tmp/scary_story_sequel.wav",
    )
```

## Usage

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

**1. Set your API key**

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

**2. Install dependencies**

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

**3. Run Agent**

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

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


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