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

Cookbook example for `litellm/audio_input_agent.py`.
"""

import requests
from agno.agent import Agent
from agno.media import Audio
from agno.models.litellm import LiteLLM

# ---------------------------------------------------------------------------
# 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

# Audio input requires specific audio-enabled models like gpt-4o-audio-preview
agent = Agent(
    model=LiteLLM(id="gpt-4o-audio-preview"),
    markdown=True,
)
agent.print_response(
    "What's the audio about?",
    audio=[Audio(content=mp3_data, format="mp3")],
    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/litellm

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

python audio_input_agent.py