livekit-plugins-silero

What it is and what it does

This package is a plugin that adds Silero voice activity detection to the LiveKit Agents framework. It enables real-time voice agents running on servers to detect when a user is speaking or has finished their turn, reducing false interruptions in conversational AI applications.

The plugin integrates with the broader LiveKit Agents ecosystem, which is designed for building multi-modal, programmable voice agents that can see, hear, and understand. It works alongside other components like speech-to-text, language models, and text-to-speech providers. The package depends on livekit-agents, numpy, and onnxruntime, making it a lightweight addition to an existing agent deployment.

Use it for:

• Detect user speech turns in real-time voice agents to minimize interruptions during conversations.
• Enable turn detection in multi-turn dialogue systems where agents need to know when to listen vs. respond.
• Integrate as a voice activity detection component within LiveKit agent deployments.
• Build telephony-integrated voice agents that handle incoming or outgoing calls with speech detection.
• Reduce latency in voice agent responses by using efficient on-device VAD.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Provides Silero voice activity detection integration for the LiveKit Agents framework to detect when users are speaking in real-time voice agent applications.

Yes. This is a focused, actively maintained plugin for a specific use case within the LiveKit Agents framework. If you are already building voice agents with LiveKit and need voice activity detection, it offers low friction installation and integrates seamlessly. If you are not using LiveKit Agents, it has no standalone value.

Install

livekit-plugins-silero on PyPI

pip install livekit-plugins-silero

uv add livekit-plugins-silero

poetry add livekit-plugins-silero

Installing livekit-plugins-silero

Before you install

Low friction install with a pure-Python wheel. Actively maintained as part of the LiveKit Agents ecosystem, with a recent release and 13002 repository stars indicating stable backing.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions, typical for open-source AI infrastructure.

Quickstart

pip install livekit-plugins-silero

from livekit.agents import Agent, AgentSession

session = AgentSession(
    vad=inference.VAD(),
    stt=inference.STT("deepgram/nova-3"),
    llm=inference.LLM("google/gemma-4-31b-it"),
    tts=inference.TTS("cartesia/sonic-3"),
)

Requires Python 3.10 or later; depends on livekit-agents, numpy, and onnxruntime.

Verify before relying

• Whether Silero VAD model is bundled or downloaded on first use, and any bandwidth/storage implications.
• Latency characteristics and accuracy metrics compared to other VAD implementations.
• Whether the plugin supports custom model weights or configuration tuning beyond defaults.

Package facts

Evidence: livekit_plugins_silero-1.6.10-py3-none-any.whl

Keywords: ai, audio, livekit, realtime, video, voice, webrtc

Tags

More Artificial Intelligence packages

Further reading