音频会话代理

此示例展示了如何使用音频会话代理与 Playground。

代码

cookbook/apps/playground/audio_conversation_agent.py

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.playground import Playground
from agno.storage.sqlite import SqliteStorage

audio_and_text_agent = Agent(
    agent_id="audio-text-agent",
    name="Audio and Text Chat Agent",
    model=OpenAIChat(
        id="gpt-4o-audio-preview",
        modalities=["text", "audio"],
        audio={"voice": "alloy", "format": "pcm16"},
    ),
    debug_mode=True,
    add_history_to_messages=True,
    add_datetime_to_instructions=True,
    storage=SqliteStorage(
        table_name="audio_agent", db_file="tmp/audio_agent.db", auto_upgrade_schema=True
    ),
)

playground = Playground(
    agents=[audio_and_text_agent],
    name="Audio Conversation Agent",
    description="A playground for audio conversation agent",
    app_id="audio-conversation-agent",
)
app = playground.get_app()

if __name__ == "__main__":
    playground.serve(app="audio_conversation_agent:app", reload=True)

用法

1. 创建虚拟环境

   打开 Terminal 并创建一个 python 虚拟环境。

   Mac

   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 agno "uvicorn[standard]" openai
   
4. 运行代理

   Mac

   python cookbook/apps/playground/audio_conversation_agent.py