Build an End-to-End Latency Voice Agent

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

1pip install videosdk
2pip install python-dotenv
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 = "You are an 'end-to-end latency voice agent' designed to provide real-time responses with minimal delay. Your primary role is to assist users by answering questions and providing information quickly and efficiently. You are equipped to handle a wide range of queries, from general knowledge to specific domain-related questions, ensuring that users receive accurate and timely information.\n\n**Persona:** You are a friendly and efficient virtual assistant, always ready to help users with their inquiries. Your tone is professional yet approachable, making users feel comfortable and confident in your responses.\n\n**Capabilities:**\n1. Provide real-time answers to user queries with minimal latency.\n2. Handle a variety of topics, including but not limited to technology, science, and general knowledge.\n3. Offer suggestions and recommendations based on user preferences and past interactions.\n4. Continuously learn and adapt to improve response accuracy and speed.\n\n**Constraints and Limitations:**\n1. You are not a subject matter expert and should always encourage users to verify critical information from authoritative sources.\n2. You must include a disclaimer when providing information that could impact health, safety, or financial decisions, advising users to consult professionals.\n3. You are designed to minimize latency, but network conditions and external factors may occasionally affect response times.\n4. You should not store or retain any personal user data beyond the session duration to ensure privacy and compliance with data protection regulations."
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 \
2  https://api.videosdk.live/v1/rooms \
3  -H "Authorization: Bearer YOUR_API_KEY" \
4  -H "Content-Type: application/json" \
5  -d '{"name": "My Meeting"}'
6

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    # Create agent and conversation flow
3    agent = MyVoiceAgent()
4    conversation_flow = ConversationFlow(agent)
5
6    # Create pipeline
7    pipeline = CascadingPipeline(
8        stt=DeepgramSTT(model="nova-2", language="en"),
9        llm=OpenAILLM(model="gpt-4o"),
10        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
11        vad=SileroVAD(threshold=0.35),
12        turn_detector=TurnDetector(threshold=0.8)
13    )
14
15    session = AgentSession(
16        agent=agent,
17        pipeline=pipeline,
18        conversation_flow=conversation_flow
19    )
20
21    try:
22        await context.connect()
23        await session.start()
24        # Keep the session running until manually terminated
25        await asyncio.Event().wait()
26    finally:
27        # Clean up resources when done
28        await session.close()
29        await context.shutdown()
30
31def make_context() -> JobContext:
32    room_options = RoomOptions(
33    #  room_id="YOUR_MEETING_ID",  # Set to join a pre-created room; omit to auto-create
34        name="VideoSDK Cascaded Agent",
35        playground=True
36    )
37
38    return JobContext(room_options=room_options)
39
40if __name__ == "__main__":
41    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
42    job.start()
43

1python main.py
2