LiveKit docs › Reference › Get Started › Recipes

---

# LiveKit Recipes

> A collection of examples, demos, and recipes for voice AI and other use cases with LiveKit and LiveKit Agents.

- **[Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md)**: Create a voice AI agent in less than 10 minutes.

- **[SwiftUI Voice Agent](https://github.com/livekit-examples/agent-starter-swift)**: A native iOS, macOS, and visionOS voice AI assistant built in SwiftUI.

- **[Next.js Voice Agent](https://github.com/livekit-examples/agent-starter-react)**: A web voice AI assistant built with React and Next.js.

- **[Flutter Voice Agent](https://github.com/livekit-examples/agent-starter-flutter)**: A cross-platform voice AI assistant app built with Flutter.

- **[React Native Voice Agent](https://github.com/livekit-examples/agent-starter-react-native)**: A native voice AI assistant app built with React Native and Expo.

- **[Android Voice Agent](https://github.com/livekit-examples/agent-starter-android)**: A native Android voice AI assistant app built with Kotlin and Jetpack Compose.

- **[Web Embed Voice Agent](https://github.com/livekit-examples/agent-starter-embed)**: A voice AI agent that can be embedded in any web page.

- **[Medical Office Triage](https://github.com/livekit-examples/python-agents-examples/tree/main/complex-agents/medical_office_triage)**: Multi-agent triage system with agent-to-agent transfers and context preservation.

- **[Healthcare Agent](https://github.com/livekit/agents/tree/main/examples/healthcare)**: Patient intake, appointment scheduling, billing, and lab results using prebuilt tasks and task groups.

- **[SpaceXAI patient intake](https://docs.livekit.io/reference/recipes/spacexai-patient-intake.md)**: A clinic front-desk agent on SpaceXAI Grok: one agent, one conversation, and a fixed surface of typed tools for scheduling, messages, and intake.

- **[Personal Shopper](https://github.com/livekit-examples/python-agents-examples/tree/main/complex-agents/personal_shopper)**: AI shopping assistant that helps find products based on user preferences.

- **[Restaurant Agent](https://docs.livekit.io/reference/recipes/restaurant-agent.md)**: A multi-agent restaurant system using handoffs and shared state between agents.

- **[LivePaint](https://github.com/livekit-examples/livepaint)**: A realtime drawing game where players compete to complete a drawing prompt while being judged by a realtime AI agent.

- **[Background audio example in Node.js](https://github.com/livekit/agents-js/blob/main/examples/src/background_audio.ts)**: A voice AI agent with background audio for ambiance.

- **[Uninterruptable Agent](https://docs.livekit.io/reference/recipes/uninterruptable.md)**: An agent that continues speaking without being interrupted.

- **[Change Language](https://docs.livekit.io/reference/recipes/changing_language.md)**: Agent that can switch between different languages during conversation.

- **[TTS Comparison](https://docs.livekit.io/reference/recipes/tts_comparison.md)**: Compare different text-to-speech providers side by side.

- **[Transcriber](https://docs.livekit.io/reference/recipes/transcriber.md)**: Real-time speech transcription with high accuracy.

- **[Keyword Detection](https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/keyword-detection/keyword_detection.py)**: Detect specific keywords in speech in real-time.

- **[Using Twilio Voice](https://docs.livekit.io/telephony/accepting-calls/inbound-twilio.md)**: Use TwiML to accept incoming calls and bridge Twilio conferencing to LiveKit via SIP.

- **[IVR Agent](https://docs.livekit.io/reference/recipes/ivr-navigator.md)**: Build a voice agent that can call external voice lines and respond to IVR flows using DTMF tones.

- **[Company Directory](https://docs.livekit.io/reference/recipes/company-directory.md)**: Build a AI company directory agent. The agent can respond to DTMF tones and voice prompts, then redirect callers.

- **[Recording Consent](https://docs.livekit.io/reference/recipes/recording-consent.md)**: Collect recording consent at the start of a call using an AgentTask for compliance and quality assurance.

- **[Phone Caller](https://docs.livekit.io/reference/recipes/make_call.md)**: Agent that can make outbound phone calls and handle conversations.

- **[SIP Lifecycle](https://docs.livekit.io/reference/recipes/sip_lifecycle.md)**: Complete lifecycle management for SIP calls.

- **[Answer Incoming Calls](https://docs.livekit.io/reference/recipes/answer_call.md)**: Set up an agent to answer incoming SIP calls.

- **[Survey Caller](https://docs.livekit.io/reference/recipes/survey_caller.md)**: Automated survey calling system.

- **[LlamaIndex RAG](https://github.com/livekit/agents/tree/main/examples/voice_agents/llamaindex-rag)**: A voice AI agent that uses LlamaIndex for RAG to answer questions from a knowledge base.

- **[Moviefone](https://docs.livekit.io/reference/recipes/moviefone.md)**: This agent uses function calling and the OpenAI API to search for movies and give you realtime information about showtimes.

- **[Context Variables](https://docs.livekit.io/reference/recipes/context_variables.md)**: Maintain conversation context across interactions.

- **[Interrupt User](https://docs.livekit.io/reference/recipes/interrupt_user.md)**: Example of how to implement user interruption in conversations.

- **[Interruptible tools](https://docs.livekit.io/agents/logic/tools/definition.md#interruptions)**: Handle or prevent interruptions in a blocking tool.

- **[LLM Content Filter](https://docs.livekit.io/reference/recipes/llm_powered_content_filter.md)**: Implement content filtering in the `llm_node`.

- **[Simple Content Filter](https://docs.livekit.io/reference/recipes/simple_content_filter.md)**: Basic content filtering implementation.

- **[LLM Output Replacement](https://docs.livekit.io/reference/recipes/replacing_llm_output.md)**: Remove chain-of-thought reasoning blocks from the LLM stream so the agent does not speak its internal reasoning aloud.

- **[Gemini Vision Assistant](https://docs.livekit.io/reference/recipes/gemini_live_vision.md)**: A voice AI agent with video input powered by Gemini Live.

- **[Raspberry Pi Transcriber](https://docs.livekit.io/reference/recipes/pi_zero_transcriber.md)**: Run transcription on Raspberry Pi hardware.

- **[Pipeline Translator](https://docs.livekit.io/reference/recipes/pipeline_translator.md)**: Implement translation in the processing pipeline.

- **[TTS Translator](https://docs.livekit.io/reference/recipes/tts_translator.md)**: Translation with text-to-speech capabilities.

- **[LLM Metrics](https://docs.livekit.io/reference/recipes/metrics_llm.md)**: Track and analyze LLM performance metrics.

- **[Realtime model metrics](https://docs.livekit.io/reference/recipes/metrics_realtime.md)**: Capture and summarize RealtimeModelMetrics for agents that use a realtime model.

- **[STT Metrics](https://docs.livekit.io/reference/recipes/metrics_stt.md)**: Track and analyze speech-to-text performance metrics.

- **[TTS Metrics](https://docs.livekit.io/reference/recipes/metrics_tts.md)**: Track and analyze text-to-speech performance metrics.

- **[VAD Metrics](https://docs.livekit.io/reference/recipes/metrics_vad.md)**: Track and analyze voice activity detection metrics.

- **[Playing Audio](https://docs.livekit.io/reference/recipes/playing_audio.md)**: Play audio files during agent interactions.

- **[Sound Repeater](https://docs.livekit.io/reference/recipes/repeater.md)**: Simple sound repeating demo for testing audio pipelines.

- **[MCP Agent](https://docs.livekit.io/reference/recipes/http_mcp_client.md)**: A voice AI agent with an integrated Model Context Protocol (MCP) client for the LiveKit API.

- **[RPC + State Agent](https://github.com/livekit-examples/python-agents-examples/tree/main/docs/examples/rpc_agent)**: Voice agent with a state database updated through tool calling and queryable from the frontend with RPC.

- **[Tavus Avatar Agent](https://github.com/livekit-examples/python-agents-examples/tree/main/complex-agents/avatars/tavus)**: An educational AI agent that uses Tavus to create an interactive study partner.

- **[Rover Teleop](https://github.com/livekit-examples/rover-teleop)**: Build a high performance robot tele-op system using LiveKit.

- **[Pan-Tilt Teleop](https://github.com/livekit-examples/teleop/tree/main/pan_tilt_demo)**: Build a realtime pan-tilt system using the LiveKit C++ SDK.

- **[C++ Examples](https://github.com/livekit-examples/cpp-example-collection)**: A collection of C++ SDK examples covering connect, publish, data, and RPC.

- **[Portal Basics](https://github.com/livekit/portal/tree/main/examples/python/basic)**: Demonstrate the complete LiveKit Portal API end to end with synthetic video.

- **[Portal Remote Inference](https://github.com/livekit/portal/tree/main/examples/python/inference)**: Run a VLA-style remote inference loop using action chunks with end-to-end latency metrics.

- **[Cloud Inference on Modal](https://github.com/livekit/portal/tree/main/examples/python/modal-mock-inference)**: Run a remote policy on Modal and measure glass-to-glass latency with a QR clock.

- **[SO-101 Teleop](https://github.com/livekit/portal/tree/main/examples/python/so101)**: Teleoperate a physical SO-101 arm over LiveKit Portal using the LeRobot plugins.

- **[Human-in-the-Loop Teleop](https://github.com/livekit-examples/portal-hitl)**: Run a human teleoperator and an ACT policy on the same robot, with mid-session control handoff.

- **[VR Spatial Video](https://github.com/livekit-examples/spatial-video)**: Stream spatial video from a stereoscopic camera to a Meta Quest using LiveKit.

- **[Echo Agent](https://github.com/livekit/agents/blob/main/examples/primitives/echo-agent.py)**: Echo user audio back to them.

- **[Drive-thru agent](https://github.com/livekit/agents/tree/main/examples/drive_thru)**: A complex food ordering agent with tasks, tools, and a complete evaluation suite.

- **[Front-desk agent](https://github.com/livekit/agents/blob/main/examples/frontdesk)**: A calendar booking agent with tasks, tools, and evaluations.

- **[Python Voice Agent](https://github.com/livekit-examples/agent-starter-python)**: A complete sample project for a voice AI agent built with Python.

- **[Warm Transfer](https://github.com/livekit/agents/tree/main/examples/warm-transfer)**: Transfer calls from an AI agent to a human operator with context.

- **[Node.js Voice Agent](https://github.com/livekit-examples/agent-starter-node)**: A complete sample project for a voice AI agent built with Node.js.

- **[Agent-assisted warm transfer](https://docs.livekit.io/telephony/features/transfers/warm.md)**: A comprehensive guide to transferring calls using an AI agent to provide context.

- **[Call forwarding using SIP REFER](https://docs.livekit.io/telephony/features/transfers/cold.md)**: How to forward calls to another number or SIP endpoint with SIP REFER.

- **[Secure trunking for SIP calls](https://docs.livekit.io/telephony/features/secure-trunking.md)**: How to enable secure trunking for LiveKit SIP.

- **[Region pinning for SIP](https://docs.livekit.io/telephony/features/region-pinning.md)**: Use region pinning to restrict calls to a specific region.

- **[Agents telephony integration](https://docs.livekit.io/agents/start/telephony.md)**: Learn how to receive and make calls with a voice AI agent

- **[LemonSlice Avatar Agent](https://github.com/livekit-examples/python-agents-examples/tree/main/complex-agents/avatars/lemonslice)**: An interactive AI agent that uses LemonSlice to practice salary negotiation.

- **[LangChain LangGraph](https://github.com/livekit-examples/python-agents-examples/tree/main/docs/examples/langchain_langgraph)**: Shows how to use a LangGraph StateGraph as the LLM backend for a LiveKit voice agent.

- **[LangChain Agent](https://github.com/livekit-examples/python-agents-examples/tree/main/docs/examples/langchain_agent)**: Shows how to use a LangChain agent with tools as the LLM backend for a LiveKit voice agent.

- **[LangChain Deep Agent](https://github.com/livekit-examples/python-agents-examples/tree/main/docs/examples/langchain_deepagent)**: A trip planning voice assistant using a LangChain deep agent, with LiveKit voice orchestration.

- **[Unity Meet](https://github.com/livekit/client-sdk-unity/tree/main/Samples~/Meet)**: A video call sample app built with Unity.

- **[Unity Voice Agent](https://github.com/livekit/client-sdk-unity/tree/main/Samples~/Agents)**: A cross-platform voice AI assistant app built with Unity.

---

This document was rendered at 2026-10-07T16:23:52.785Z.
For the latest version of this document, see [https://docs.livekit.io/reference/recipes.md](https://docs.livekit.io/reference/recipes.md).

To explore all LiveKit documentation, see [llms.txt](https://docs.livekit.io/llms.txt).