LuxePlatforms
Rather just talk?(816) 477-6802hello@luxeplatforms.comKansas City · Building nationwide
AI Voice SaaS · Local Business03 / 16

A self-running platform that finds local businesses, demos an AI receptionist, and answers their phones

Discovery to a live AI agent, with a human only clicking “convert.”

An AI receptionist business in a box. It discovers local businesses that miss calls, sends personalized cold outreach with a free interactive voice demo, and converts paying clients into live AI phone agents end to end, with a human only clicking “convert.”

In production

A look at the interface.

Representative UI — abstracted, never a client's real data.
🔒chat.workspace.dev
New chat
Recent
Quarterly report draft
Refactor billing logic
Summarize call notes
Schema migration plan
Workspace · Pro
AssistantonlineOpus 4.8 ⌄
Pull last quarter's numbers from the PDF and chart revenue vs target.
analyze_document(Q4-report.pdf)done
Revenue
$128k
Target
$110k
Δ
+16%
Revenue came in 16% above target. The lift is driven by Q4 enterprise renewals — here's the breakdown:
  • Enterprise +$22k (renewals)
  • Self-serve flat MoM
[1] Q4-report.pdf[2] forecast.xlsx
Ask anything…Opus 4.8
AI / conversational · representative UI
24/7
Answers every call, day or night
Live
Handling real phone calls
13
Industries it speaks for
Role
Solo, full-stack + voice infra
Year
2026
Status
In production
Category
AI Voice SaaS · Local Business
Built with
  • Next.js
  • Supabase
  • Twilio
  • Pipecat
  • Deepgram
  • Stripe Connect
  • GCP
(01) The Challenge

Small local businesses lose real revenue to missed and after-hours calls but can't afford a 24/7 receptionist. LuxeVoice solves both the customer's missed-call problem and its own lead generation, automating discovery, outreach, onboarding, billing, and live call handling as one self-running pipeline.

(02) The Approach

How it
works

Inbound calls route over SIP into a low-latency pipeline chaining speech-to-text, an LLM, and streaming text-to-speech. A daily job discovers and scores prospects 0–100, generates each a personalized voice demo, then fires multi-step cold email. On payment, an LLM scrapes the client's site to author a custom agent prompt and a phone number is provisioned automatically. No human setup anywhere in the loop.

What I built

(03) Inside the build
01

Real-time call agent

Twilio routes inbound calls over SIP into a Pipecat pipeline chaining speech-to-text, an LLM, and low-latency text-to-speech for natural conversation.

02

Automated outreach engine

A daily job discovers and scores prospects 0–100, builds each a personalized voice demo, and fires multi-step cold-email sequences with auto follow-ups.

03

Self-provisioning agents

On payment, an LLM scrapes the client's site to author a custom agent prompt and Twilio provisions a local number automatically, with no human setup.

(04) Highlights

The
receipts

  • Zero-touch pipeline: discovery → demo → outreach → onboarding → live agent
  • Self-hosted demo stack keeps each voice demo at ~$0.0006
  • ~80% gross margin on calls; break-even at a single client
  • 13 supported industries with per-vertical voices and scripts
← Previous
Social Fitness Meetup App
Next →
Marketplace for Teachers