VAD Metrics | LiveKit Documentation

This example shows you how to log voice-activity-detection (VAD) metrics during a call. Each time the VAD processes speech, it emits idle time and inference timing data that you render with Rich.

Note

This recipe uses the per-plugin metrics_collected event on the VAD instance. This per-component surface is not deprecated. A separate session-level metrics_collected event (session.on("metrics_collected", ...)) is deprecated. For session-scoped cost and usage tracking, see Session usage.

Prerequisites

Add a .env.local in this directory with your LiveKit credentials:

LIVEKIT_URL=your_livekit_url
LIVEKIT_API_KEY=your_api_key
LIVEKIT_API_SECRET=your_api_secret

Install dependencies:

pip install rich "livekit-agents" python-dotenv

Load environment, logging, and define an AgentServer

Set up dotenv, logging, a Rich console for the VAD reports, and initialize the AgentServer.

import logging
import asyncio
from dotenv import load_dotenv
from livekit.agents import JobContext, AgentServer, cli, Agent, AgentSession, inference
from livekit.agents.metrics import VADMetrics
from rich.console import Console
from rich.table import Table
from rich import box
from datetime import datetime

load_dotenv(".env.local")

logger = logging.getLogger("metrics-vad")
logger.setLevel(logging.INFO)

console = Console()

server = AgentServer()

Define a lightweight agent and VAD metrics display function

Keep the Agent class minimal with just instructions. Define an async function to display VAD metrics as a Rich table.

class VADMetricsAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions="You are a helpful agent."
        )

async def display_vad_metrics(metrics: VADMetrics):
    table = Table(
        title="[bold blue]VAD Metrics Report[/bold blue]",
        box=box.ROUNDED,
        highlight=True,
        show_header=True,
        header_style="bold cyan"
    )

    table.add_column("Metric", style="bold green")
    table.add_column("Value", style="yellow")

    timestamp = datetime.fromtimestamp(metrics.timestamp).strftime('%Y-%m-%d %H:%M:%S')

    table.add_row("Type", str(metrics.type))
    table.add_row("Label", str(metrics.label))
    table.add_row("Timestamp", timestamp)
    table.add_row("Idle Time", f"[white]{metrics.idle_time:.4f}[/white]s")
    table.add_row("Inference Duration Total", f"[white]{metrics.inference_duration_total:.4f}[/white]s")
    table.add_row("Inference Count", str(metrics.inference_count))

    console.print("\n")
    console.print(table)
    console.print("\n")

Define the rtc session with VAD metrics hook

Create an rtc session entrypoint that builds an inference.VAD instance, hooks into its metrics_collected event, and starts the agent session with STT/LLM/TTS configuration. Passing the instance to AgentSession as vad replaces the bundled VAD so the same object emits the metrics you display.

@server.rtc_session(agent_name="my-agent")
async def entrypoint(ctx: JobContext):
    ctx.log_context_fields = {"room": ctx.room.name}

    vad_instance = inference.VAD(model="silero")

    def on_vad_metrics(metrics: VADMetrics):
        asyncio.create_task(display_vad_metrics(metrics))

    vad_instance.on("metrics_collected", on_vad_metrics)

    session = AgentSession(
        stt=inference.STT(model="deepgram/nova-3-general"),
        llm=inference.LLM(model="google/gemma-4-31b-it"),
        tts=inference.TTS(model="inworld/inworld-tts-2", voice="Ashley"),
        vad=vad_instance,
        preemptive_generation=True,
    )

    await session.start(agent=VADMetricsAgent(), room=ctx.room)
    await ctx.connect()

Run the server

The cli.run_app() function starts the agent server. It manages the worker lifecycle, connects to LiveKit, and processes incoming jobs.

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

Run it

lk agent console metrics_vad.py

How it works

When the rtc session starts, the metrics_collected event handler is attached to the VAD.
The VAD detects speech and emits metrics events with idle time, inference duration, and count.
A background task formats and prints the metrics as a Rich table.
Because the handler is async, it does not block ongoing audio processing.

Full example

import logging
import asyncio
from dotenv import load_dotenv
from livekit.agents import JobContext, AgentServer, cli, Agent, AgentSession, inference
from livekit.agents.metrics import VADMetrics
from rich.console import Console
from rich.table import Table
from rich import box
from datetime import datetime

load_dotenv(".env.local")

logger = logging.getLogger("metrics-vad")
logger.setLevel(logging.INFO)

console = Console()

class VADMetricsAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions="You are a helpful agent."
        )

async def display_vad_metrics(metrics: VADMetrics):
    table = Table(
        title="[bold blue]VAD Metrics Report[/bold blue]",
        box=box.ROUNDED,
        highlight=True,
        show_header=True,
        header_style="bold cyan"
    )

    table.add_column("Metric", style="bold green")
    table.add_column("Value", style="yellow")

    timestamp = datetime.fromtimestamp(metrics.timestamp).strftime('%Y-%m-%d %H:%M:%S')

    table.add_row("Type", str(metrics.type))
    table.add_row("Label", str(metrics.label))
    table.add_row("Timestamp", timestamp)
    table.add_row("Idle Time", f"[white]{metrics.idle_time:.4f}[/white]s")
    table.add_row("Inference Duration Total", f"[white]{metrics.inference_duration_total:.4f}[/white]s")
    table.add_row("Inference Count", str(metrics.inference_count))

    console.print("\n")
    console.print(table)
    console.print("\n")

server = AgentServer()

@server.rtc_session(agent_name="my-agent")
async def entrypoint(ctx: JobContext):
    ctx.log_context_fields = {"room": ctx.room.name}

    vad_instance = inference.VAD(model="silero")

    def on_vad_metrics(metrics: VADMetrics):
        asyncio.create_task(display_vad_metrics(metrics))

    vad_instance.on("metrics_collected", on_vad_metrics)

    session = AgentSession(
        stt=inference.STT(model="deepgram/nova-3-general"),
        llm=inference.LLM(model="google/gemma-4-31b-it"),
        tts=inference.TTS(model="inworld/inworld-tts-2", voice="Ashley"),
        vad=vad_instance,
        preemptive_generation=True,
    )

    await session.start(agent=VADMetricsAgent(), room=ctx.room)
    await ctx.connect()

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