Gemini models support text, audio, images and videos as input.

1

Setup your virtual environment

python3 -m venv .venv
source .venv/bin/activate
2

Install dependencies

pip install -U google-genai duckduckgo-search agno
3

Export your Google API key

export GOOGLE_API_KEY=***
4

Run the agent

python agent.py

​
Example: Audio Agent

from agno.agent import Agent
from agno.media import Audio
from agno.models.google import Gemini

agent = Agent(
    model=Gemini(id="gemini-2.0-flash-exp"),
    markdown=True,
)

url = "https://openaiassets.blob.core.windows.net/$web/API/docs/audio/alloy.wav"

agent.print_response(
    "Tell me about this audio",
    audio=[Audio(url=url)],
)

​
Example: Image Agent

from agno.agent import Agent
from agno.media import Image
from agno.models.google import Gemini
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=Gemini(id="gemini-2.0-flash-exp"),
    tools=[DuckDuckGoTools()],
    markdown=True,
)

agent.print_response(
    "Tell me about this image and search the web for more information.",
    images=[
        Image(
            url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg"
        ),
    ],
)

​
Example: Video Agent

from pathlib import Path

from agno.agent import Agent
from agno.media import Video
from agno.models.google import Gemini

agent = Agent(
    model=Gemini(id="gemini-2.0-flash-exp"),
    markdown=True,
)

# Run: `wget https://storage.googleapis.com/generativeai-downloads/images/GreatRedSpot.mp4` to download a sample video
video_path = Path(__file__).parent.joinpath("sample_video.mp4")

agent.print_response("Tell me about this video?", videos=[Video(filepath=video_path)])

​
View More Examples

OpenAIAnthropic