Recipes

Create a voice AI agent in less than 10 minutes.

A native iOS, macOS, and visionOS voice AI assistant built in SwiftUI.

A web voice AI assistant built with React and Next.js.

A cross-platform voice AI assistant app built with Flutter.

A native voice AI assistant app built with React Native and Expo.

A native Android voice AI assistant app built with Kotlin and Jetpack Compose.

A voice AI agent that can be embedded in any web page.

Multi-agent triage system with agent-to-agent transfers and context preservation.

Patient intake, appointment scheduling, billing, and lab results using prebuilt tasks and task groups.

A clinic front-desk agent on SpaceXAI Grok: one agent, one conversation, and a fixed surface of typed tools for scheduling, messages, and intake.

AI shopping assistant that helps find products based on user preferences.

A multi-agent restaurant system using handoffs and shared state between agents.

A realtime drawing game where players compete to complete a drawing prompt while being judged by a realtime AI agent.

A voice AI agent with background audio for ambiance.

An agent that continues speaking without being interrupted.

Agent that can switch between different languages during conversation.

Compare different text-to-speech providers side by side.

Real-time speech transcription with high accuracy.

Detect specific keywords in speech in real-time.

Use TwiML to accept incoming calls and bridge Twilio conferencing to LiveKit via SIP.

Build a voice agent that can call external voice lines and respond to IVR flows using DTMF tones.

Build a AI company directory agent. The agent can respond to DTMF tones and voice prompts, then redirect callers.

Collect recording consent at the start of a call using an AgentTask for compliance and quality assurance.

Agent that can make outbound phone calls and handle conversations.

Complete lifecycle management for SIP calls.

Set up an agent to answer incoming SIP calls.

Automated survey calling system.

A voice AI agent that uses LlamaIndex for RAG to answer questions from a knowledge base.

This agent uses function calling and the OpenAI API to search for movies and give you realtime information about showtimes.

Maintain conversation context across interactions.

Example of how to implement user interruption in conversations.

Handle or prevent interruptions in a blocking tool.

Implement content filtering in the `llm_node`.

Basic content filtering implementation.

Remove chain-of-thought reasoning blocks from the LLM stream so the agent does not speak its internal reasoning aloud.

A voice AI agent with video input powered by Gemini Live.

Run transcription on Raspberry Pi hardware.

Implement translation in the processing pipeline.

Translation with text-to-speech capabilities.

Track and analyze LLM performance metrics.

Capture and summarize RealtimeModelMetrics for agents that use a realtime model.

Track and analyze speech-to-text performance metrics.

Track and analyze text-to-speech performance metrics.

Track and analyze voice activity detection metrics.

Play audio files during agent interactions.

Simple sound repeating demo for testing audio pipelines.

A voice AI agent with an integrated Model Context Protocol (MCP) client for the LiveKit API.

Voice agent with a state database updated through tool calling and queryable from the frontend with RPC.

An educational AI agent that uses Tavus to create an interactive study partner.

Build a high performance robot tele-op system using LiveKit.

Build a realtime pan-tilt system using the LiveKit C++ SDK.

A collection of C++ SDK examples covering connect, publish, data, and RPC.

Demonstrate the complete LiveKit Portal API end to end with synthetic video.

Run a VLA-style remote inference loop using action chunks with end-to-end latency metrics.

Run a remote policy on Modal and measure glass-to-glass latency with a QR clock.

Teleoperate a physical SO-101 arm over LiveKit Portal using the LeRobot plugins.

Run a human teleoperator and an ACT policy on the same robot, with mid-session control handoff.

Stream spatial video from a stereoscopic camera to a Meta Quest using LiveKit.

Echo user audio back to them.

A complex food ordering agent with tasks, tools, and a complete evaluation suite.

A calendar booking agent with tasks, tools, and evaluations.

A complete sample project for a voice AI agent built with Python.

Transfer calls from an AI agent to a human operator with context.

A complete sample project for a voice AI agent built with Node.js.

A comprehensive guide to transferring calls using an AI agent to provide context.

How to forward calls to another number or SIP endpoint with SIP REFER.

How to enable secure trunking for LiveKit SIP.

Use region pinning to restrict calls to a specific region.

Learn how to receive and make calls with a voice AI agent

An interactive AI agent that uses LemonSlice to practice salary negotiation.

Shows how to use a LangGraph StateGraph as the LLM backend for a LiveKit voice agent.

Shows how to use a LangChain agent with tools as the LLM backend for a LiveKit voice agent.

A trip planning voice assistant using a LangChain deep agent, with LiveKit voice orchestration.

A video call sample app built with Unity.

A cross-platform voice AI assistant app built with Unity.