Audio Multi Turn

This example demonstrates how to create an agent that can handle multi-turn audio conversations, maintaining context between audio interactions while generating both text and audio responses.

Code

audio_multi_turn.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file
from rich.pretty import pprint

agent = Agent(
    model=OpenAIChat(
        id="gpt-5-mini-audio-preview",
        modalities=["text", "audio"],
        audio={"voice": "sage", "format": "wav"},
    ),
    add_history_to_context=True,
    db=SqliteDb(
        session_table="audio_multi_turn_sessions", db_file="tmp/audio_multi_turn.db"
    ),
)

run_response = agent.run("Is a golden retriever a good family dog?")
pprint(run_response.content)
if run_response.response_audio is not None:
    write_audio_to_file(
        audio=run_response.response_audio.content, filename="tmp/answer_1.wav"
    )

run_response = agent.run("What breed are we talking about?")
pprint(run_response.content)
if run_response.response_audio is not None:
    write_audio_to_file(
        audio=run_response.response_audio.content, filename="tmp/answer_2.wav"
    )

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

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

   pip install -U openai agno
   
3. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Create a Python file

   Create a Python file and add the above code.

   touch audio_multi_turn.py
   
5. Run Agent

   Mac

   python audio_multi_turn.py
   
6. Find All Cookbooks

   Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

   Agno Cookbooks on GitHub