LiveKit quickstart

mkdir aic-livekit-python
cd aic-livekit-python
uv venv --python 3.11
source .venv/bin/activate
uv pip install "ai-coustics-livekit-extras==0.26.0" "aic-sdk==3.4.0" "livekit-agents==1.8.2" "python-dotenv==1.2.2"

mkdir aic-livekit-node
cd aic-livekit-node
npm init -y
npm pkg set type=module
npm install --save-exact @ai-coustics/livekit-extras@0.26.0 @ai-coustics/aic-sdk@0.26.0 @livekit/agents@1.9.0 @livekit/rtc-node@0.13.35 dotenv@17.4.1
npm install --save-dev --save-exact tsx@4.20.6 typescript@5.9.3 @types/node@24.10.1

python -c 'from aic_sdk import Model; from shutil import copyfile; path = Model.download("vad-ms-2.1-xxs-16khz", "models"); print(copyfile(path, "models/vad.aicmodel"))'

node --input-type=module -e 'import { Model } from "@ai-coustics/livekit-extras"; import { copyFileSync } from "node:fs"; const path = await Model.download("vad-ms-2.1-xxs-16khz", "models"); copyFileSync(path, "models/vad.aicmodel"); console.log("models/vad.aicmodel");'

import logging
import os

from dotenv import load_dotenv
from livekit.agents import (
    Agent, AgentServer, AgentSession, JobContext, JobProcess,
    cli, inference, room_io,
)
from ai_coustics.livekit import VAD, Model

load_dotenv(".env.local")
logger = logging.getLogger("aic-example")

server = AgentServer()


def prewarm(proc: JobProcess):
    proc.userdata["vad_model"] = Model.from_file("models/vad.aicmodel")


server.setup_fnc = prewarm


@server.rtc_session(agent_name="aic-vad-demo")
async def entrypoint(ctx: JobContext):
    key = os.environ.get("AIC_SDK_LICENSE", "").strip()
    if not key:
        raise RuntimeError("Set AIC_SDK_LICENSE in .env.local and restart the agent")

    vad = VAD(model=ctx.proc.userdata["vad_model"], license_key=key)

    @vad.on("metrics_collected")
    def on_vad_metrics(metrics):
        logger.info("AIC VAD inference count: %s", metrics.inference_count)

    session = AgentSession(
        vad=vad,
        stt=inference.STT("deepgram/nova-3", language="multi"),
        llm=inference.LLM("openai/gpt-4.1-mini"),
        tts=inference.TTS("cartesia/sonic-3"),
    )
    await session.start(
        agent=Agent(instructions="You are a helpful voice assistant. Keep replies brief."),
        room=ctx.room,
        room_options=room_io.RoomOptions(
            audio_input=room_io.AudioInputOptions(
                sample_rate=16000,
                num_channels=1,
                noise_cancellation=vad.processor,
            ),
        ),
    )
    await ctx.connect()


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

import { cli, defineAgent, inference, ServerOptions, voice } from '@livekit/agents';
import { Model, VAD } from '@ai-coustics/livekit-extras';
import dotenv from 'dotenv';
import { fileURLToPath } from 'node:url';

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

export default defineAgent({
  prewarm: (proc) => {
    proc.userData.vadModel = Model.fromFile('models/vad.aicmodel');
  },
  entry: async (ctx) => {
    const key = process.env.AIC_SDK_LICENSE?.trim();
    if (!key) throw new Error('Set AIC_SDK_LICENSE in .env.local and restart the agent');

    const vad = new VAD({ model: ctx.proc.userData.vadModel as Model, licenseKey: key });
    const session = new voice.AgentSession({
      vad,
      stt: new inference.STT({ model: 'deepgram/nova-3', language: 'multi' }),
      llm: new inference.LLM({ model: 'openai/gpt-4.1-mini' }),
      tts: new inference.TTS({ model: 'cartesia/sonic-3' }),
    });
    await session.start({
      agent: new voice.Agent({ instructions: 'You are a helpful voice assistant. Keep replies brief.' }),
      room: ctx.room,
      inputOptions: {
        audioSampleRate: 16000,
        audioNumChannels: 1,
        noiseCancellation: vad.processor,
      },
    });
    await ctx.connect();
  },
});

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

python agent.py dev

npx tsx agent.ts dev