LiveWire | SignalWire

LiveWire is a compatibility layer that lets developers familiar with livekit-agents use the same class and function names while running on SignalWire infrastructure. Change your import path and your existing code runs on SignalWire with no other modifications.

# Before (livekit-agents)
from livekit.agents import Agent, AgentSession, function_tool
# After (SignalWire LiveWire)
from signalwire.livewire import Agent, AgentSession, function_tool

SignalWire’s control plane handles STT, TTS, VAD, and turn detection automatically. Pipeline plugin parameters (stt, tts, vad, turn_detection) are accepted for API compatibility but are no-ops. LiveWire logs an informational message the first time each no-op parameter is used.

Quick Start

from signalwire.livewire import (
    Agent,
    AgentSession,
    AgentServer,
    JobContext,
    JobProcess,
    function_tool,
    run_app,
)
@function_tool
def lookup_order(order_id: str) -> str:
    """Look up the status of a customer order."""
    return f"Order {order_id} shipped yesterday."
server = AgentServer()
@server.rtc_session()
async def entrypoint(ctx: JobContext):
    agent = Agent(
        instructions="You are a helpful order-status assistant.",
        tools=[lookup_order],
    )
    session = AgentSession()
    await session.start(agent, room=ctx.room)
run_app(server)

Namespace Aliases

LiveWire provides namespace objects that mirror common livekit-agents import paths:

Alias	Contents	Mirrors
`voice`	`Agent`, `AgentSession`	`livekit.agents.voice`
`llm_ns`	`tool` (alias for `function_tool`), `ToolError`, `ChatContext`	`livekit.agents.llm`
`cli_ns`	`run_app`	`livekit.agents.cli`
`inference`	`STT`, `LLM`, `TTS`	`livekit.agents.inference`

from signalwire.livewire import voice, llm_ns, inference
agent = voice.Agent(instructions="Hello")
session = voice.AgentSession(llm=inference.LLM(model="gpt-4o"))