代码
import requests
from agno.agent import Agent
from agno.media import Audio
from agno.models.google import Gemini
agent = Agent(
model=Gemini(id="gemini-2.0-flash-exp"),
markdown=True,
)
url = "https://agno-public.s3.us-east-1.amazonaws.com/demo_data/QA-01.mp3"
response = requests.get(url)
audio_content = response.content
agent.print_response(
"转录此次音频对话内容，使用说话人 A、说话人 B 来区分不同的说话人。",
audio=[Audio(content=audio_content)],
stream=True,
)