Voice AI quickstart

from dotenv import load_dotenv

from livekit import agents
from livekit.agents import AgentServer, AgentSession, Agent, inference, room_io, TurnHandlingOptions
from livekit.plugins import ai_coustics

load_dotenv(".env.local")


class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions="""You are a helpful voice AI assistant.
            You eagerly assist users with their questions by providing information from your extensive knowledge.
            Your responses are concise, to the point, and without any complex formatting or punctuation including emojis, asterisks, or other symbols.
            You are curious, friendly, and have a sense of humor.""",
        )

server = AgentServer()

@server.rtc_session(agent_name="my-agent")
async def my_agent(ctx: agents.JobContext):
    session = AgentSession(
        stt=inference.STT(model="assemblyai/universal-3-6-pro", language="en"),
        llm=inference.LLM(model="google/gemma-4-31b-it"),
        tts=inference.TTS(
            model="fishaudio/s2.1-pro",
            voice="fa4c9eb3dccc4806b382b40d61c6b10a",
        ),
        turn_handling=TurnHandlingOptions(
            turn_detection=inference.TurnDetector(),
        ),
    )

    await session.start(
        room=ctx.room,
        agent=Assistant(),
        room_options=room_io.RoomOptions(
            audio_input=room_io.AudioInputOptions(
                noise_cancellation=ai_coustics.audio_enhancement(model=ai_coustics.EnhancerModel.QUAIL_VF_S),
            ),
        ),
    )

    await session.generate_reply(
        instructions="Greet the user and offer your assistance."
    )


if __name__ == "__main__":
    agents.cli.run_app(server)

import {
  type JobContext,
  ServerOptions,
  cli,
  defineAgent,
  inference,
  voice,
} from '@livekit/agents';
import * as aiCoustics from '@livekit/plugins-ai-coustics';
import { fileURLToPath } from 'node:url';
import dotenv from 'dotenv';
import { createAgent } from './agent';

dotenv.config({ path: '.env.local' });

export default defineAgent({
  entry: async (ctx: JobContext) => {
    const session = new voice.AgentSession({
      stt: new inference.STT({ model: 'assemblyai/universal-3-6-pro', language: 'en' }),
      llm: new inference.LLM({ model: 'google/gemma-4-31b-it' }),
      tts: new inference.TTS({
        model: 'fishaudio/s2.1-pro',
        voice: 'fa4c9eb3dccc4806b382b40d61c6b10a',
      }),
      turnHandling: {
        turnDetection: new inference.TurnDetector(),
      },
    });

    await session.start({
      agent: createAgent(),
      room: ctx.room,
      inputOptions: {
        noiseCancellation: aiCoustics.audioEnhancement({ model: aiCoustics.EnhancerModel.QuailVfS }),
      },
    });

    await ctx.connect();

    const handle = session.generateReply({
      instructions: 'Greet the user and offer your assistance.',
    });
  },
});

cli.runApp(new ServerOptions({ agent: fileURLToPath(import.meta.url), agentName: 'my-agent' }));

import { voice } from '@livekit/agents';

export function createAgent() {
  return voice.Agent.create({
    instructions: `You are a helpful voice AI assistant.
      You eagerly assist users with their questions by providing information from your extensive knowledge.
      Your responses are concise, to the point, and without any complex formatting or punctuation including emojis, asterisks, or other symbols.
      You are curious, friendly, and have a sense of humor.`,
  });
}

from dotenv import load_dotenv

from livekit import agents
from livekit.agents import AgentServer, AgentSession, Agent, inference, room_io
from livekit.plugins import ai_coustics

load_dotenv(".env.local")

class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(instructions="You are a helpful voice AI assistant.")

server = AgentServer()

@server.rtc_session(agent_name="my-agent")
async def my_agent(ctx: agents.JobContext):
    session = AgentSession(
        llm=inference.RealtimeModel(
            model="openai/gpt-realtime-2.1",
            voice="marin",
        )
    )

    await session.start(
        room=ctx.room,
        agent=Assistant(),
        room_options=room_io.RoomOptions(
            audio_input=room_io.AudioInputOptions(
                noise_cancellation=ai_coustics.audio_enhancement(model=ai_coustics.EnhancerModel.QUAIL_VF_S),
            ),
        ),
    )

    await session.generate_reply(
        instructions="Greet the user and offer your assistance. You should start by speaking in English."
    )


if __name__ == "__main__":
    agents.cli.run_app(server)

import {
  type JobContext,
  ServerOptions,
  cli,
  defineAgent,
  inference,
  voice,
} from '@livekit/agents';
import * as aiCoustics from '@livekit/plugins-ai-coustics';
import { fileURLToPath } from 'node:url';
import dotenv from 'dotenv';
import { createAgent } from './agent';

dotenv.config({ path: '.env.local' });

export default defineAgent({
  entry: async (ctx: JobContext) => {
    const session = new voice.AgentSession({
      llm: new inference.RealtimeModel({
        model: 'openai/gpt-realtime-2.1',
        voice: 'marin',
      }),
    });

    await session.start({
      agent: createAgent(),
      room: ctx.room,
      inputOptions: {
        noiseCancellation: aiCoustics.audioEnhancement({ model: aiCoustics.EnhancerModel.QuailVfS }),
      },
    });

    await ctx.connect();

    await session.generateReply({
      instructions: 'Greet the user and offer your assistance. You should start by speaking in English.',
    });
  },
});

cli.runApp(new ServerOptions({ agent: fileURLToPath(import.meta.url), agentName: 'my-agent' }));

import { voice } from '@livekit/agents';

export function createAgent() {
  return voice.Agent.create({
    instructions: 'You are a helpful voice AI assistant.',
  });
}