​
代码

cookbook/models/openai/chat/audio_input_agent.py
import requests
from agno.agent import Agent, RunResponse  # noqa
from agno.media import Audio
from agno.models.openai import OpenAIChat

# 获取音频文件并将其转换为base64编码字符串
url = "https://openaiassets.blob.core.windows.net/$web/API/docs/audio/alloy.wav"
response = requests.get(url)
response.raise_for_status()
wav_data = response.content

# 为Agent提供音频文件并获取文本结果
agent = Agent(
    model=OpenAIChat(id="gpt-4o-audio-preview", modalities=["text"]),
    markdown=True,
)
agent.print_response(
    "这段音频说了什么？", audio=[Audio(content=wav_data, format="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 requests agno
4

运行Agent

python cookbook/models/openai/chat/audio_input_agent.py