Build a Voice Agent Infrastructure

1sequenceDiagram
2    participant User
3    participant Agent
4    participant STT
5    participant LLM
6    participant TTS
7    User->>Agent: Speak
8    Agent->>STT: Convert Speech to Text
9    STT->>LLM: Process Text
10    LLM->>TTS: Generate Response
11    TTS->>Agent: Convert Text to Speech
12    Agent->>User: Respond
13

1python -m venv venv
2source venv/bin/activate  # On Windows use `venv\\Scripts\\activate`
3

1pip install videosdk-agents videosdk-plugins-silero videosdk-plugins-turn-detector videosdk-plugins-deepgram videosdk-plugins-openai videosdk-plugins-elevenlabs
2

1import asyncio, os
2from videosdk.agents import Agent, AgentSession, CascadingPipeline, JobContext, RoomOptions, WorkerJob, ConversationFlow
3from videosdk.plugins.silero import SileroVAD
4from videosdk.plugins.turn_detector import TurnDetector, pre_download_model
5from videosdk.plugins.deepgram import DeepgramSTT
6from videosdk.plugins.openai import OpenAILLM
7from videosdk.plugins.elevenlabs import ElevenLabsTTS
8from typing import AsyncIterator
9
10# Pre-downloading the Turn Detector model
11pre_download_model()
12
13agent_instructions = "You are a 'Voice Agent Infrastructure Specialist', designed to assist users in understanding and implementing voice agent systems. Your primary role is to provide guidance on setting up and managing the infrastructure required for voice agents. You can explain technical concepts, recommend best practices, and troubleshoot common issues related to voice agent infrastructure. However, you are not a certified network engineer or IT professional, and you must advise users to consult with qualified experts for complex network configurations or security concerns. Your responses should be clear, concise, and focused on infrastructure-related topics, avoiding any unrelated technical support or advice."
14
15class MyVoiceAgent(Agent):
16    def __init__(self):
17        super().__init__(instructions=agent_instructions)
18    async def on_enter(self): await self.session.say("Hello! How can I help?")
19    async def on_exit(self): await self.session.say("Goodbye!")
20
21async def start_session(context: JobContext):
22    # Create agent and conversation flow
23    agent = MyVoiceAgent()
24    conversation_flow = ConversationFlow(agent)
25
26    # Create pipeline
27    pipeline = CascadingPipeline(
28        stt=DeepgramSTT(model="nova-2", language="en"),
29        llm=OpenAILLM(model="gpt-4o"),
30        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
31        vad=SileroVAD(threshold=0.35),
32        turn_detector=TurnDetector(threshold=0.8)
33    )
34
35    session = AgentSession(
36        agent=agent,
37        pipeline=pipeline,
38        conversation_flow=conversation_flow
39    )
40
41    try:
42        await context.connect()
43        await session.start()
44        # Keep the session running until manually terminated
45        await asyncio.Event().wait()
46    finally:
47        # Clean up resources when done
48        await session.close()
49        await context.shutdown()
50
51def make_context() -> JobContext:
52    room_options = RoomOptions(
53    #  room_id="YOUR_MEETING_ID",  # Set to join a pre-created room; omit to auto-create
54        name="VideoSDK Cascaded Agent",
55        playground=True
56    )
57
58    return JobContext(room_options=room_options)
59
60if __name__ == "__main__":
61    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
62    job.start()
63

1curl -X POST 'https://api.videosdk.live/v1/meetings' \
2-H 'Authorization: YOUR_API_KEY' \
3-H 'Content-Type: application/json'
4

1python main.py
2