GA SignalWire

SignalWire AI Agent (SWML)

Telephony platform with a built-in AI agent runtime defined declaratively in SWML: one per-minute rate covers realtime STT, the LLM and standard TTS, plus SWAIG function calling to your webhooks.

Est. per minute$0.163 - 0.168

Overview

Best for: Phone agents where one predictable bundled rate including the LLM is preferred.

At a glance

Platform $/min$0.16
All-in priceYes
Entry plan $/mo$0
Phone numbersYes
WebRTCYes
Phone / SIPYes
Self-hostNo
Open weightsNo

$0.16/min includes STT, LLM and standard TTS; voice transport and premium voices extra. Bundled LLM not named.

Audio in

Phone/SIP/WebRTC

Audio out

Standard TTS included; ElevenLabs/premium TTS extra

Languages

Configurable via ai.languages or ai.multilingual.

Latency

No verified number.

Regions

Not verified.

Compliance

Not verified in this research.

Features

  • telephony
  • function calling (SWAIG)
  • post-call summary webhook (post_prompt_url)
  • barge-in
  • memory
  • retrieval
  • pronunciation hints

Pricing

WhatPriceUnitNotes
AI Agent Runtime$0.16per minuteIncludes STT, LLM and standard TTS.
Local inbound / outbound$0.0066 / $0.008per minuteSIP and WebRTC $0.003/min.
Local number$0.50per monthToll-free $0.80/month; port-out $5/number.
ElevenLabs TTS$0.000297per characterHigh quality $0.000594/char; page is inconsistent on how premium TTS is billed for agents.
How the per-minute estimate was worked out

SignalWire's own all-in estimate for standard SIP/PSTN usage with standard TTS. Premium/ElevenLabs voices add more.

Free tier: Not stated on pricing page.

Source: signalwire.com

Setup

  1. Create a SignalWire space and buy a number.
  2. Create a SWML script (dashboard or hosted URL) with answer + ai.
  3. Point the number's call handler at the SWML; add SWAIG functions that call your webhooks; set post_prompt_url for call summaries.

Endpoint

SWML served from your URL or the dashboard

Authentication

Project ID + API token

Quick start javascript

// Serve a minimal SWML AI agent (JSON form of SWML) from Express
import express from "express";
const app = express();
app.all("/swml", (req, res) => res.json({
  version: "1.0.0",
  sections: {
    main: [
      { answer: {} },
      { ai: {
          prompt: { text: "You are a customer service agent for Acme. Say you are an AI. Be brief." },
          post_prompt: { text: "Summarize the call and any actions taken." },
          post_prompt_url: "https://example.com/post-prompt-hook"
      } }
    ]
  }
}));
app.listen(3000);

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Premium voices cost extra

Standard TTS is included; ElevenLabs is billed per character and the page is inconsistent about how it applies to agents. Price your exact voice.

Higher headline than DIY

$0.16/min bundled is roughly 2x a DIY Twilio/Plivo + cheap model stack, but includes the LLM.

SWML learning curve

Agent behaviour lives in SWML/SWAIG rather than code, which is fast to start but different from Python/JS frameworks.

LLM choice

The bundled LLM is chosen by SignalWire; confirm which models and whether you can bring your own.

Plus 12 warnings that apply to all platforms and telephony APIs. See category warnings.

Limits

  • Not published in sources reviewed

Models and products

NameStatusNotes
AI Agent RuntimeGA$0.16/min including real-time STT, LLM and standard TTS; orchestration, barge-in, memory, tool calls and retrieval included. Voice transport billed separately.

Docs and sources

Docs

Sources used

Not fully verified

Which LLM is bundled; free trial; compliance.

Similar platforms APIs

Spotted a wrong price or a dead link?