Build Your First Voice Agent using LiveKit

1
import logging
2
from dotenv import load_dotenv
3
from livekit.agents import JobContext, WorkerOptions, cli
4
from livekit.agents.voice import Agent, AgentSession
5
from livekit.plugins import openai, sarvam
6
7
# Load environment variables
8
load_dotenv()
9
10
# Set up logging
11
logger = logging.getLogger("voice-agent")
12
logger.setLevel(logging.INFO)
13
14
15
class VoiceAgent(Agent):
16
    def __init__(self) -> None:
17
        super().__init__(
18
            # Your agent's personality and instructions
19
            instructions="""
20
                You are a helpful voice assistant.
21
                Be friendly, concise, and conversational.
22
                Speak naturally as if you're having a real conversation.
23
            """,
24
            
25
            # Saarika STT - Converts speech to text
26
            stt=sarvam.STT(
27
                language="unknown",  # Auto-detect language, or use "en-IN", "hi-IN", etc.
28
                model="saarika:v2.5"
29
            ),
30
            
31
            # OpenAI LLM - The "brain" that processes and generates responses
32
            llm=openai.LLM(model="gpt-4o"),
33
            
34
            # Bulbul TTS - Converts text to speech
35
            tts=sarvam.TTS(
36
                target_language_code="en-IN",
37
                model="bulbul:v2",
38
                speaker="anushka"  # Female: anushka, manisha, vidya, arya | Male: abhilash, karun, hitesh
39
            ),
40
        )
41
    
42
    async def on_enter(self):
43
        """Called when user joins - agent starts the conversation"""
44
        self.session.generate_reply()
45
46
47
async def entrypoint(ctx: JobContext):
48
    """Main entry point - LiveKit calls this when a user connects"""
49
    logger.info(f"User connected to room: {ctx.room.name}")
50
    
51
    # Create and start the agent session
52
    session = AgentSession()
53
    await session.start(
54
        agent=VoiceAgent(),
55
        room=ctx.room
56
    )
57
58
59
if __name__ == "__main__":
60
    # Run the agent
61
    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))

1
stt=sarvam.STT(
2
    language="hi-IN",  # Hindi
3
    model="saarika:v2.5"
4
),
5
tts=sarvam.TTS(
6
    target_language_code="hi-IN",
7
    model="bulbul:v2",
8
    speaker="manisha"  # Or: anushka, vidya, arya, abhilash, karun, hitesh
9
)

1
stt=sarvam.STT(language="ta-IN", model="saarika:v2.5"),
2
tts=sarvam.TTS(
3
    target_language_code="ta-IN",
4
    model="bulbul:v2",
5
    speaker="anushka"
6
)

1
stt=sarvam.STT(language="unknown", model="saarika:v2.5"),  # Auto-detects language
2
tts=sarvam.TTS(target_language_code="en-IN", model="bulbul:v2", speaker="karun")

1
# User speaks Hindi → Saaras converts to English → LLM processes → Responds in English
2
3
stt=sarvam.STT(model="saaras:v2.5"),  # Speech-to-English translation
4
llm=openai.LLM(model="gpt-4o"),
5
tts=sarvam.TTS(target_language_code="en-IN", model="bulbul:v2", speaker="abhilash")