Skip to main content
The Line SDK is a Python framework for building voice agents. Handles audio infrastructure, speech recognition, and conversation flow.
New to Line? Start with the Quickstart to build and deploy your first agent.

Core Concepts

ComponentPurpose
AgentControls the input/output event loop via a process method
LlmAgentBuilt-in agent that wraps 100+ LLM providers via LiteLLM
ToolsFunctions your agent can call—database lookups, handoffs, web search
VoiceAgentAppHTTP server that connects your agent to Cartesia’s audio infrastructure
The agent speaks the introduction when a call starts, then responds to whatever the user says using the LLM.

Features

  • Real-time interruption support — Handles audio interruptions and turn-taking out-of-the-box.
  • Tool calling — Connect to databases, APIs, and external services
  • Multi-agent handoffs — Route conversations between specialized agents
  • Web search — Built-in tool for real-time information lookup

Add Capabilities

Look up information

Handoff to another agent

Search the web

See Tools for the full guide.

Code Examples

ExampleDescription
Basic ChatSimple conversational agent
Chat SupervisorFast chat model with powerful reasoning escalation
Form FillerCollect structured data via conversation
Multi-AgentHand off between specialized agents

Integrations

IntegrationDescription
Exa Web ResearchReal-time web search
BrowserbaseFill web forms via voice

Next Steps

Agents

Configure prompts, LLMs, and conversation flow

Tools

Add custom tools and multi-agent handoffs