Strands Agent の BidiAgent と OpenAI Realtime API を利用して音声がインターフェイスのエージェントを作ってみた #AWSreInvent

from strands import Agent
from strands_tools import calculator

agent = Agent(tools=[calculator])

# Single request-response cycle
result = agent("Calculate 25 * 48")
print(result.message)  # "The result is 1200"

import asyncio
from strands.experimental.bidi import BidiAgent, BidiAudioIO
from strands.experimental.bidi.models import BidiNovaSonicModel

model = BidiNovaSonicModel()
agent = BidiAgent(model=model, tools=[calculator])
audio_io = BidiAudioIO()

async def main():
    # Persistent connection with continuous streaming
    await agent.run(
        inputs=[audio_io.input()],
        outputs=[audio_io.output()]
    )

asyncio.run(main())

uv init
uv add "strands-agents-tools" "strands-agents[bidi,bidi-all,bidi-openai]"

export OPENAI_API_KEY=your_api_key

import asyncio

from strands.experimental.bidi import BidiAgent
from strands.experimental.bidi.io import BidiAudioIO, BidiTextIO
from strands.experimental.bidi.models.openai_realtime import BidiOpenAIRealtimeModel
from strands.experimental.bidi.tools import stop_conversation

from strands_tools import calculator

async def main() -> None:
    model = BidiOpenAIRealtimeModel(
        model_id="gpt-realtime",
        provider_config={
            "audio": {
                "voice": "coral",
            }
        },
    )
    # stop_conversation tool allows user to verbally stop agent execution.
    agent = BidiAgent(
        model=model,
        tools=[calculator, stop_conversation],
        system_prompt="You are a helpful assistant that can use the calculator tool to calculate numbers.",
    )

    audio_io = BidiAudioIO()
    text_io = BidiTextIO()
    await agent.run(inputs=[audio_io.input()], outputs=[audio_io.output(), text_io.output()])

if __name__ == "__main__":
    asyncio.run(main())