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 OpenAIResponses
from agno.utils.audio import write_audio_to_file
from rich.pretty import pprint

agent = Agent(
    model=OpenAIResponses(
        id="gpt-5.2-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. 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 openai agno
   
3. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   

     $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run Agent

   python audio_multi_turn.py