Build an AI Voice Agent for Disambiguation

1python -m venv venv
2source venv/bin/activate  # On Windows use `venv\\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
10pre_download_model()
11
12agent_instructions = "You are a conversational AI Voice Agent specializing in disambiguation in conversation. Your persona is that of a friendly and knowledgeable guide who assists users in clarifying ambiguous statements or questions during conversations. Your primary capability is to identify potential ambiguities in user input and provide options or ask follow-up questions to clarify the user's intent. You can also offer examples to illustrate different interpretations of ambiguous phrases. However, you are not capable of making decisions or providing advice beyond clarification. You must always remind users to provide more context if needed and encourage them to specify their queries for better assistance. You are not a subject matter expert in any specific field, so you should refrain from providing detailed advice or information outside the scope of disambiguation. Always include a disclaimer that your role is to assist in clarifying communication and not to provide expert advice."
13
14class MyVoiceAgent(Agent):
15    def __init__(self):
16        super().__init__(instructions=agent_instructions)
17    async def on_enter(self): await self.session.say("Hello! How can I help?")
18    async def on_exit(self): await self.session.say("Goodbye!")
19
20async def start_session(context: JobContext):
21    agent = MyVoiceAgent()
22    conversation_flow = ConversationFlow(agent)
23
24    pipeline = CascadingPipeline(
25        stt=DeepgramSTT(model="nova-2", language="en"),
26        llm=OpenAILLM(model="gpt-4o"),
27        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
28        vad=SileroVAD(threshold=0.35),
29        turn_detector=TurnDetector(threshold=0.8)
30    )
31
32    session = [AgentSession](https://docs.videosdk.live/ai_agents/core-components/agent-session)(
33        agent=agent,
34        pipeline=pipeline,
35        conversation_flow=conversation_flow
36    )
37
38    try:
39        await context.connect()
40        await session.start()
41        await asyncio.Event().wait()
42    finally:
43        await session.close()
44        await context.shutdown()
45
46def make_context() -> JobContext:
47    room_options = RoomOptions(
48    #  room_id="YOUR_MEETING_ID",  # Set to join a pre-created room; omit to auto-create
49        name="VideoSDK Cascaded Agent",
50        playground=True
51    )
52
53    return JobContext(room_options=room_options)
54
55if __name__ == "__main__":
56    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
57    job.start()
58

1curl -X POST \
2  https://api.videosdk.live/v1/meetings \
3  -H "Authorization: Bearer YOUR_API_KEY" \
4  -H "Content-Type: application/json"
5

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
5    pipeline = CascadingPipeline(
6        stt=DeepgramSTT(model="nova-2", language="en"),
7        llm=OpenAILLM(model="gpt-4o"),
8        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
9        vad=SileroVAD(threshold=0.35),
10        turn_detector=TurnDetector(threshold=0.8)
11    )
12
13    session = AgentSession(
14        agent=agent,
15        pipeline=pipeline,
16        conversation_flow=conversation_flow
17    )
18
19    try:
20        await context.connect()
21        await session.start()
22        await asyncio.Event().wait()
23    finally:
24        await session.close()
25        await context.shutdown()
26
27if __name__ == "__main__":
28    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
29    job.start()
30

1python main.py
2