Overview
Building a great voice AI app requires careful orchestration of multiple components. LiveKit Agents is built on top of the Realtime SDK to provide dedicated abstractions that simplify development while giving you full control over the underlying code.
Voice AI providers
You can choose from a variety of providers for each part of the voice pipeline to fit your needs. The framework supports both high-performance STT-LLM-TTS pipelines and speech-to-speech models. In either case, the framework automatically manages interruptions, transcription forwarding, turn detection, and more.
You may add these components to the AgentSession, where they act as global defaults within the app, or to each individual Agent if needed.
Capabilities
The following guides, in addition to others in this section, cover the core capabilities of the AgentSession and how to leverage them in your app.
Workflows
Core constructs for building complex voice AI workflows.
Agent sessions
An agent session orchestrates your voice AI app's lifecycle.
Agents & handoffs
Define agents and agent handoffs to build multi-agent voice AI workflows.
Tool definition & use
Use tools to call external services, inject custom logic, and more.
Tasks & task groups
Use tasks and task groups to execute discrete operations and build complex workflows.
Pipeline nodes
Add custom behavior to any component of the voice pipeline.