Skip to main content
"""
Openai Audio Input Agent
========================

Cookbook example for `openai/chat/audio_input_agent.py`.
"""

import requests
from agno.agent import Agent, RunOutput  # noqa
from agno.media import Audio
from agno.models.openai import OpenAIChat

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

# 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

# Provide the agent with the audio file and get result as text
agent = Agent(
    model=OpenAIChat(id="gpt-4o-audio-preview", modalities=["text"]),
    markdown=True,
)
agent.print_response(
    "What is in this audio?", audio=[Audio(content=wav_data, format="wav")], stream=True
)

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

if __name__ == "__main__":
    pass

​
Run the Example

# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/90_models/openai/chat

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python audio_input_agent.py