Trillions of Minutes. Now With an AI Kernel.

The team that built FreeSWITCH extended the same platform with native AI. Same codebase. Same engineers. Two decades of voice infrastructure behind every call.

2.7B minutes and messages annually
2,000+ companies in production
20 years continuous development
< 1.2s typical AI response latency

Why Heritage Matters

Voice Infrastructure Is a Solved Problem (If You Built It)

Media Stack Ownership

The team wrote the media engine that powers voice networks worldwide. They can modify codecs, endpointing, and AI at the audio-frame level.

Known Failure Modes

Two decades of production telephony means codec, buffering, endpoint, and billing edge cases are already catalogued.

Engine-Level AI

The AI kernel coordinates STT, inference, and TTS with direct access to the audio stream.

End-to-End Changes

One team modifies one codebase. No vendor ticket, compatibility wait, or external orchestration layer.

Build a Voice AI Agent

Python
TypeScript
Go
Java
Ruby
PHP
Perl
C++
C#

from signalwire import AgentBase
from signalwire.core.function_result import FunctionResult

class SupportAgent(AgentBase):
    def __init__(self):
        super().__init__(name="Support Agent", route="/support")
        self.prompt_add_section("Instructions",
            body="You are a customer support agent. \
            Greet the caller and resolve their issue.")
        self.add_language("English", "en-US", "rime.spore:mistv2")

@AgentBase.tool(name="check_order")
    def check_order(self, order_id: str):
        """Check the status of a customer order.
        Args:
            order_id: The order ID to look up
        """
        return FunctionResult(f"Order {order_id}: shipped, ETA April 2nd")

agent = SupportAgent()
agent.run()

Bolt-On AI vs. Embedded AI Kernel

Bolt-On Architecture

Separate telephony, STT, TTS, and LLM providers, each with its own SDK. Your glue code manages state across all four services. Each vendor adds a separate queue, invoice, and escalation path. Compliance and observability must be rebuilt across every vendor. 16 to 23 months before a production call.

Embedded AI Kernel

Telephony, STT, TTS, and LLM in one platform. AI runs inside the media stack, not outside it. 800–1200ms typical response latency. One vendor, one invoice, one escalation path. Production calls in four to six weeks. State management is platform-native.

Platform Evolution

From Open-Source Engine to Cloud Platform

2006: FreeSWITCH Created

An open-source telephony engine built for carrier-scale media processing.

2018–2020: Real-Time Cloud Platform

Real-time WebSocket control and a managed cloud platform brought the engine to developers.

2023–2024: AI Kernel and Governed Inference

AI orchestration moved inside the media engine with production controls and observability.

2025: Agents SDK

Composable agents, scoped prompts, tools, and tests across multiple languages. Try it now.

Sigmond Runs on SignalWire

A voice and video AI agent built on the SignalWire SDK, wired to a live knowledge base, able to see what you show him. Build the same thing on voice, phone, WhatsApp, or SIP, or an entire white-label platform with SignalWire as the network underneath.

Call recording

This call is recorded. Audio and transcripts are used to improve our AI and customer support experience, and aren't shared or sold to third parties.

Trusted by 2,000+ Companies

Build on Two Decades of Voice Infrastructure

One pip install. The same engine that powers carrier-grade telephony worldwide.