Recipes

Create a voice AI agent in less than 10 minutes.

Agent that triages patients based on symptoms and medical history.

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

A restaurant front-of-house agent that can take orders, add items to a shared cart, and checkout.

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

A voice AI agent that uses push-to-talk for controlled multi-participant conversations, only enabling audio input when explicitly triggered.

A voice AI agent with background audio for thinking states and 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.

Agent that can make outbound phone calls and handle conversations.

Transfer calls from an AI agent to a human operator seamlessly.

Complete lifecycle management for SIP calls.

Set up an agent to answer incoming SIP calls.

Automated survey calling system.

Build an agent for chain-of-thought reasoning using the `llm_node` to clean the text before TTS.

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

An agent that can answer questions using RAG.

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.

Implement content filtering in the `llm_node`.

Basic content filtering implementation.

Example of modifying LLM output before processing.

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

Run transcription on Raspberry Pi hardware.

Implement translation in the processing pipeline.

Translation with text-to-speech capabilities.

Track and analyze LLM performance metrics.

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.