Google Audio Input File Upload

Upload an MP3 through the Gemini Files API and reuse the remote file across runs.

The source passes a Google uploaded File object to Audio.content, which accepts bytes in Agno v2.7.4. Use the local file path directly before running.

audio_input_file_upload.py

"""
Google Audio Input File Upload
==============================

Cookbook example for `google/gemini/audio_input_file_upload.py`.
"""

from pathlib import Path

from agno.agent import Agent
from agno.media import Audio
from agno.models.google import Gemini
from google.genai.types import UploadFileConfig

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

model = Gemini(id="gemini-3.5-flash")
agent = Agent(
    model=model,
    markdown=True,
)

# Please download a sample audio file to test this Agent and upload using:
audio_path = Path(__file__).parent.joinpath("sample.mp3")
audio_file = None

remote_file_name = f"files/{audio_path.stem.lower()}"
try:
    audio_file = model.get_client().files.get(name=remote_file_name)
except Exception as e:
    print(f"Error getting file {audio_path.stem}: {e}")
    pass

if not audio_file:
    try:
        audio_file = model.get_client().files.upload(
            file=audio_path,
            config=UploadFileConfig(name=audio_path.stem, display_name=audio_path.stem),
        )
        print(f"Uploaded audio: {audio_file}")
    except Exception as e:
        print(f"Error uploading audio: {e}")

agent.print_response(
    "Tell me about this audio",
    audio=[Audio(content=audio_file)],
    stream=True,
)

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

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno google-genai
   
3. Export your Google API key

   Mac/Linux

   export GOOGLE_API_KEY="your_google_api_key_here"
   

   $Env:GOOGLE_API_KEY="your_google_api_key_here"
   
4. Use the local audio directly

   Remove the UploadFileConfig import and the remote file lookup and upload block. Replace Audio(content=audio_file) with Audio(filepath=audio_path).

5. Add the sample audio

   Place an MP3 named sample.mp3 next to the saved script, or update audio_path to point to your audio file.

6. Run the example

   Save the code above as audio_input_file_upload.py, then run:

   python audio_input_file_upload.py
   

Full source: cookbook/90_models/google/gemini/audio_input_file_upload.py