​
代码

from pathlib import Path

from agno.agent import Agent, RunResponse
from agno.media import Image
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file
from rich import print
from rich.text import Text

image_agent = Agent(model=OpenAIChat(id="gpt-4o"))

image_path = Path(__file__).parent.joinpath("sample.jpg")
image_story: RunResponse = image_agent.run(
    "请根据图片写一个三句话的虚构故事",
    images=[Image(filepath=image_path)],
)
formatted_text = Text.from_markup(
    f":sparkles: [bold magenta]故事:[/bold magenta] {image_story.content} :sparkles:"
)
print(formatted_text)

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

audio_story: RunResponse = audio_agent.run(
    f"请富有感情地朗读这个故事：{image_story.content}"
)
if audio_story.response_audio is not None:
    write_audio_to_file(
        audio=audio_story.response_audio.content, filename="tmp/sample_story.wav"
    )

​
使用方法

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 rich agno
4

运行智能体

python cookbook/agent_concepts/multimodal/image_to_audio.py