livekit-plugins-deepgram

import os import asyncio from livekit.agents import llm, stt, tts, vad from livekit.agents.voice_assistant import VoiceAssistant from livekit.agents.utils import AudioStream from livekit.plugins import deepgram, openai, silero # Ensure Deepgram API key is set in environment variables or passed directly os.environ['DEEPGRAM_API_KEY'] = os.environ.get('DEEPGRAM_API_KEY', 'your_deepgram_api_key_here') os.environ['OPENAI_API_KEY'] = os.environ.get('OPENAI_API_KEY', 'your_openai_api_key_here') async def main(): # Example using Deepgram for STT and TTS, and OpenAI for LLM deepgram_stt = deepgram.STT(model='nova-2') deepgram_tts = deepgram.TTS(model='aura-2-asteria-en') openai_llm = openai.LLM(model='gpt-4o-mini') silero_vad = silero.VAD.get_default_vad() assistant = VoiceAssistant( stt=deepgram_stt, tts=deepgram_tts, llm=openai_llm, vad=silero_vad, context_timeout=15, # seconds interrupt_sensitivity=0.5, ) print("VoiceAssistant initialized. You can now use deepgram_stt, deepgram_tts in your agent session.") # In a real agent, you would integrate this into an AgentSession # For example: AgentSession(llm=openai_llm, stt=deepgram_stt, tts=deepgram_tts, ...) # Simulate text-to-speech async for chunk in deepgram_tts.synthesize('Hello from LiveKit and Deepgram!'): if chunk.type == AudioStream.Type.ELEMENT: print(f"Received audio chunk: {len(chunk.data)} bytes") if __name__ == '__main__': asyncio.run(main())