​
代码

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file

agent = Agent(
    model=OpenAIChat(
        id="gpt-4o-audio-preview",
        modalities=["text", "audio"],
        audio={"voice": "alloy", "format": "wav"},
    ),
    debug_mode=True,
    add_history_to_messages=True,
)

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

agent.run("Why do you say they are loyal?")
if agent.run_response.response_audio is not None:
    write_audio_to_file(
        audio=agent.run_response.response_audio.content, filename="tmp/answer_2.wav"
    )

​
用法

1

创建虚拟环境

打开 Terminal 并创建一个 python 虚拟环境。

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

设置您的 API 密钥

export OPENAI_API_KEY=xxx
3

安装库

pip install -U openai agno
4

运行代理

python cookbook/agent_concepts/multimodal/audio_multi_turn.py