Building a voice AI stack from scratch takes six vendors, three engineers, and a year of glue code before your first production call.
Sigmond is a voice AI agent running on the SignalWire infrastructure this page is about. Ask him about anything you just read.

STT, TTS, LLM, and telephony providers each require proof-of-concept testing. Two to three months pass before you write any integration code.
Race conditions, zombie calls, double updates. Conversation context scattered across four independent systems with no shared state model.
When one vendor in a five-vendor chain fails, your code handles the fallback. Each failure mode requires its own mitigation path.
Four or five dashboards, each showing a partial picture. Building unified monitoring and correlated logs is a project unto itself.
PCI scope reduction, data isolation, and audit logging must happen across every vendor independently. One audit surface becomes five.
from signalwire_agents import AgentBase
from signalwire_agents.core.function_result import SwaigFunctionResult
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 SwaigFunctionResult(f"Order {order_id}: shipped, ETA April 2nd")
agent = SupportAgent()
agent.run()
| Component | DIY Stack | SignalWire |
|---|---|---|
| Transport (PSTN/SIP) | $700-1,500 | Carrier rates (separate) |
| STT provider | $400-800 | Included |
| LLM provider | $1,000-4,000+ | Included |
| TTS provider | $500-2,000 | Included |
| Infrastructure | $500-1,500 | $50-200 (your agent hosting) |
| Engineering (2-3 FTEs maintaining glue) | $40,000-75,000 | $0 incremental |
| Total | $43,100-84,800 | $1,650-1,800 |
We evaluated building in-house. Six vendors, twelve months of integration work, and three engineers dedicated to infrastructure. SignalWire replaced all of it with one platform.
pip install signalwire-agents. Define your agent class, add a prompt, run it. Make your first phone call to a working AI agent.
Add tool functions that call your backend. Order lookups, appointment scheduling, account verification. The tools that differentiate your product.
Define steps with scoped prompts and scoped tools. Each step handles one phase of the conversation with focused context.
Test with real calls. Iterate on prompts and flows. Use the sandbox environment for rapid development cycles.
Deploy your agent as a standard HTTP microservice. Provision phone numbers. Route calls. You are in production.
The platform is model-agnostic. Changing providers is a configuration update. Your agent code, tools, and tests stay the same.
Update the agent configuration. The platform handles multilingual STT and TTS natively. No new vendor integrations required.
One vendor, one data flow, one audit surface. Compare that to auditing four or five independent systems with separate data handling policies.
Yes. Start with telephony replacement and add platform capabilities at your own pace. Each phase delivers value independently.
One platform, one SLA, one escalation path. No finger-pointing between vendors when something breaks at 2am.
Trusted by 2,000+ companies
Build on infrastructure designed for voice AI, not assembled from six vendors.
SignalWire is a communications infrastructure platform. Voice, video, messaging, conferencing, queuing, recording, and AI all run on the same real-time voice and video substrate.
AI is one capability among many, not the whole business. Customers compose multiple services on a single carrier-billed call; margin expands as the service mix shifts toward higher-margin capabilities stacked on top of the transport layer.
The platform was built by the team that created FreeSWITCH. It processes 2.7 billion minutes and messages annually and is in production at 2,000+ companies, including Apple, Sprinklr, Deutsche Telekom, and T-Mobile.