pipinstall'openai-agents[voice]'

importasyncioimportrandomfromagentsimport(Agent,function_tool,)fromagents.extensions.handoff_promptimportprompt_with_handoff_instructions@function_tooldefget_weather(city:str)->str:"""Get the weather for a given city."""print(f"[debug] get_weather called with city:{city}")choices=["sunny","cloudy","rainy","snowy"]returnf"The weather in{city} is{random.choice(choices)}."spanish_agent=Agent(name="Spanish",handoff_description="A spanish speaking agent.",instructions=prompt_with_handoff_instructions("You're speaking to a human, so be polite and concise. Speak in Spanish.",),model="gpt-5.2",)agent=Agent(name="Assistant",instructions=prompt_with_handoff_instructions("You're speaking to a human, so be polite and concise. If the user speaks in Spanish, handoff to the spanish agent.",),model="gpt-5.2",handoffs=[spanish_agent],tools=[get_weather],)

fromagents.voiceimportSingleAgentVoiceWorkflow,VoicePipelinepipeline=VoicePipeline(workflow=SingleAgentVoiceWorkflow(agent))

importnumpyasnpimportsounddeviceassdfromagents.voiceimportAudioInput# For simplicity, we'll just create 3 seconds of silence# In reality, you'd get microphone databuffer=np.zeros(24000*3,dtype=np.int16)audio_input=AudioInput(buffer=buffer)result=awaitpipeline.run(audio_input)# Create an audio player using `sounddevice`player=sd.OutputStream(samplerate=24000,channels=1,dtype=np.int16)player.start()# Play the audio stream as it comes inasyncforeventinresult.stream():ifevent.type=="voice_stream_event_audio":player.write(event.data)

importasyncioimportrandomimportnumpyasnpimportsounddeviceassdfromagentsimport(Agent,function_tool,set_tracing_disabled,)fromagents.voiceimport(AudioInput,SingleAgentVoiceWorkflow,VoicePipeline,)fromagents.extensions.handoff_promptimportprompt_with_handoff_instructions@function_tooldefget_weather(city:str)->str:"""Get the weather for a given city."""print(f"[debug] get_weather called with city:{city}")choices=["sunny","cloudy","rainy","snowy"]returnf"The weather in{city} is{random.choice(choices)}."spanish_agent=Agent(name="Spanish",handoff_description="A spanish speaking agent.",instructions=prompt_with_handoff_instructions("You're speaking to a human, so be polite and concise. Speak in Spanish.",),model="gpt-5.2",)agent=Agent(name="Assistant",instructions=prompt_with_handoff_instructions("You're speaking to a human, so be polite and concise. If the user speaks in Spanish, handoff to the spanish agent.",),model="gpt-5.2",handoffs=[spanish_agent],tools=[get_weather],)asyncdefmain():pipeline=VoicePipeline(workflow=SingleAgentVoiceWorkflow(agent))buffer=np.zeros(24000*3,dtype=np.int16)audio_input=AudioInput(buffer=buffer)result=awaitpipeline.run(audio_input)# Create an audio player using `sounddevice`player=sd.OutputStream(samplerate=24000,channels=1,dtype=np.int16)player.start()# Play the audio stream as it comes inasyncforeventinresult.stream():ifevent.type=="voice_stream_event_audio":player.write(event.data)if__name__=="__main__":asyncio.run(main())