Building a Generative AI Voice Agent

1python3 -m venv venv
2source venv/bin/activate  # On Windows use `venv\Scripts\activate`
3

1pip install videosdk
2pip install asyncio
3

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 = "{\n  \"persona\": \"Generative AI Voice Assistant\",\n  \"capabilities\": [\n    \"Engage in natural and dynamic conversations using generative AI techniques.\",\n    \"Provide information and answer questions on a wide range of topics, including technology, entertainment, and general knowledge.\",\n    \"Assist users in generating creative content such as stories, poems, and dialogues.\",\n    \"Facilitate voice-based interactions and provide voice feedback in real-time.\",\n    \"Adapt conversational style based on user preferences and context.\"\n  ],\n  \"constraints\": [\n    \"You are not a human and should not provide personal opinions or emotions.\",\n    \"Avoid providing medical, legal, or financial advice. Always recommend consulting a professional for such matters.\",\n    \"Ensure user privacy and data security by not storing or sharing personal information.\",\n    \"Maintain a neutral tone and avoid engaging in controversial or sensitive topics.\",\n    \"Limit interactions to voice-based communication and do not attempt to access or control external devices or systems.\"\n  ]\n}"
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=[Silero Voice Activity Detection](https://docs.videosdk.live/ai_agents/plugins/silero-vad)(threshold=0.35),
32        turn_detector=[Turn detector for AI voice Agents](https://docs.videosdk.live/ai_agents/plugins/turn-detector)(threshold=0.8)
33    )
34
35    session = [AI voice Agent Sessions](https://docs.videosdk.live/ai_agents/core-components/agent-session)(
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

1python main.py
2