Build AI Voice Agents for Public Services

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-->>Agent: Text
10    Agent->>LLM: Process Text
11    LLM-->>Agent: Response Text
12    Agent->>TTS: Convert Text to Speech
13    TTS-->>Agent: Audio
14    Agent->>User: Speak
15

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

1pip install videosdk
2

1VIDEOSDK_API_KEY=your_api_key_here
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 an AI Voice Agent designed to assist with public services inquiries. Your persona is that of a knowledgeable and courteous public service representative. Your primary capabilities include providing information about various public services such as healthcare, transportation, and utilities, assisting users in navigating public service websites, and answering frequently asked questions related to public services. You can also guide users on how to access specific services and provide contact information for further assistance. However, you must adhere to the following constraints: you are not a legal or medical professional, so you must include a disclaimer advising users to consult with qualified professionals for legal or medical advice. Additionally, you should not store any personal data or make any transactions on behalf of users. Your responses should be concise, accurate, and respectful, ensuring a positive user experience."
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: Bearer YOUR_API_KEY" \\
3-H "Content-Type: application/json"
4

1class MyVoiceAgent(Agent):
2    def __init__(self):
3        super().__init__(instructions=agent_instructions)
4    async def on_enter(self): await self.session.say("Hello! How can I help?")
5    async def on_exit(self): await self.session.say("Goodbye!")
6

1pipeline = CascadingPipeline(
2    stt=DeepgramSTT(model="nova-2", language="en"),
3    llm=OpenAILLM(model="gpt-4o"),
4    tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
5    vad=SileroVAD(threshold=0.35),
6    turn_detector=TurnDetector(threshold=0.8)
7)
8

1async def start_session(context: JobContext):
2    agent = MyVoiceAgent()
3    conversation_flow = ConversationFlow(agent)
4    pipeline = CascadingPipeline(
5        stt=DeepgramSTT(model="nova-2", language="en"),
6        llm=OpenAILLM(model="gpt-4o"),
7        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
8        vad=SileroVAD(threshold=0.35),
9        turn_detector=TurnDetector(threshold=0.8)
10    )
11    session = AgentSession(
12        agent=agent,
13        pipeline=pipeline,
14        conversation_flow=conversation_flow
15    )
16    try:
17        await context.connect()
18        await session.start()
19        await asyncio.Event().wait()
20    finally:
21        await session.close()
22        await context.shutdown()
23

1python main.py
2