import asyncio
import signal
import vocode
from vocode.streaming.streaming_conversation import StreamingConversation
from vocode.helpers import create_streaming_microphone_input_and_speaker_output
from vocode.streaming.models.transcriber import (
DeepgramTranscriberConfig,
PunctuationEndpointingConfig,
)
from vocode.streaming.agent.chat_gpt_agent import ChatGPTAgent
from vocode.streaming.models.agent import ChatGPTAgentConfig
from vocode.streaming.models.message import BaseMessage
from vocode.streaming.models.synthesizer import AzureSynthesizerConfig
from vocode.streaming.synthesizer.azure_synthesizer import AzureSynthesizer
from vocode.streaming.transcriber.deepgram_transcriber import DeepgramTranscriber
# these can also be set as environment variables
vocode.setenv(
OPENAI_API_KEY="<your OpenAI key>",
DEEPGRAM_API_KEY="<your Deepgram key>",
AZURE_SPEECH_KEY="<your Azure key>",
AZURE_SPEECH_REGION="<your Azure region>",
)
async def main():
microphone_input, speaker_output = create_streaming_microphone_input_and_speaker_output(
use_default_devices=True,
)
conversation = StreamingConversation(
output_device=speaker_output,
transcriber=DeepgramTranscriber(
DeepgramTranscriberConfig.from_input_device(
microphone_input, endpointing_config=PunctuationEndpointingConfig()
)
),
agent=ChatGPTAgent(
ChatGPTAgentConfig(
initial_message=BaseMessage(text="Hello!"),
prompt_preamble="Have a pleasant conversation about life",
),
),
synthesizer=AzureSynthesizer(
AzureSynthesizerConfig.from_output_device(speaker_output)
),
)
await conversation.start()
print("Conversation started, press Ctrl+C to end")
signal.signal(
signal.SIGINT, lambda _0, _1: asyncio.create_task(conversation.terminate())
)
while conversation.is_active():
chunk = await microphone_input.get_audio()
conversation.receive_audio(chunk)
if __name__ == "__main__":
asyncio.run(main())
