The LiveKit Agents plugin interface makes it easy to adopt the best AI providers for your app, without needing customized code for each.
Installing plugins
Each provider is available as a separate plugin package, included as an optional dependency on the base SDK for Python. For example, to install the SDK with the Cartesia, Deepgram, and OpenAI plugins, run the following command:
pip install livekit-agents[cartesia,deepgram,openai]~=1.0rc
You may also install plugins as individual packages. For example, this is equivalent to the previous command:
pip install \livekit-agents~=1.0rc \livekit-plugins-cartesia~=1.0rc \livekit-plugins-deepgram~=1.0rc \livekit-plugins-openai~=1.0rc
Plugin directory and reference
Browse the following sections for documentation on each type of plugin:
Realtime models
Plugins for multimodal speech-to-speech models like the OpenAI Realtime API.
Large Language Models (LLM)
Plugins for AI models from OpenAI, Anthropic, and more.
Speech-to-text (STT)
Plugins for speech-to-text solutions like Deepgram, Whisper, and more.
Text-to-speech (TTS)
Plugins for text-to-speech solutions like Cartesia, ElevenLabs, and more.
Other plugins
The following additional specialized plugins are available:
Enhanced noise cancellation
LiveKit Cloud enhanced noise cancellation.
Silero VAD
Silero voice activity detection (VAD).
Turn detection
Custom LiveKit model for End-of-Turn detection.
Browser
Chromium Embedded Framework (CEF) for LiveKit Agents
RAG utilities
A collection of tools to assist with Retrieval-Augmented Generation (RAG).
NLTK
Utilities for working with text using Natural Language Toolkit (NLTK).
LlamaIndex
Support for LlamaIndex query engine and chat engine.
Annoy
Vector retrieval with Annoy.
Building your own
The plugin framework is extensible and community-driven. Your plugin can integrate with various providers or directly load models for local inference.
By adopting the standard interfaces, you can abstract away implementation specifics and simplify switching between different providers in your agent code.
Code contributions to plugins are always welcome. To learn more, see the guidelines for contributions to the Python repository or the Node.js repository.