← Case Studies
Case Study · The Infinite Story Engine · February 2026

Voice-Powered AI Storytelling, Built & Deployed End-to-End

A real-time interactive narration app where users speak to an AI storyteller that crafts personalized audio adventures — two engine modes, live transcription, and full session analytics.

2
Engine Modes
$0.06
Per Minute
Live
MVP Deployed
The Pipeline

How it works

SpeakTalk to the narrator
NarrateAI tells the story
ChoosePick from 4 paths
ContinueStory evolves
The Client

The Infinite Story Engine

The Infinite Story Engine is an interactive storytelling platform that lets users create personalized audio adventures using just their voice. The client wanted an MVP that could demonstrate real-time voice-to-AI narration in the browser — complete with user authentication, session tracking, and detailed analytics to test with early users and gather feedback.

The Vision

Speak your story into existence

Nick envisioned a platform where anyone could step into a story just by speaking. No typing, no menus — just a conversation with an AI narrator who listens, adapts, and brings your adventure to life in real time. He needed a team to take this from concept to a fully working, deployed product that real users could test.

Two Engine Modes

One app, two ways to power it

We built two distinct engine modes so the client could test different approaches with real users and compare quality vs. latency.

Mode 1
Grok Voice (Speech-to-Speech)
Single voice-to-voice AI model via xAI's Grok Realtime API. Ultra-low latency with a natural conversational feel — one model handles listening, thinking, and speaking.
xAI Grok
Mode 2
HD Pipeline (Multi-Model)
Three specialized models working in sequence: Deepgram Nova-3 for speech recognition, Claude Sonnet 4.6 for story generation, and ElevenLabs for cinematic text-to-speech narration.
DeepgramClaudeElevenLabs
What We Built

Full-stack MVP, deployed and live

Real-Time Voice via LiveKit
WebRTC-powered voice connection between browser and AI agent. Handles audio streaming, connection state, and mobile audio compatibility.
LiveKitWebRTC
Next.js Frontend
TypeScript and Tailwind CSS. Responsive UI with live transcript, countdown timer, session controls, and engine mode selection.
Next.jsTailwindTypeScript
Auth & Analytics via Supabase
User authentication with email/password login. Session analytics tracking duration, latency, feedback ratings, and cost estimates.
Supabase
Deployed on DigitalOcean
Dockerized app on the client's own VPS. Nginx reverse proxy, SSL via Let's Encrypt, connected to their custom domain.
DigitalOceanDockerNginx
The Results

What this delivered

2
Engine Modes
Grok Voice and HD Pipeline for real-world A/B testing
$0.06
Per Minute
Both modes optimized to ~$0.06/min with prompt caching
Live
MVP Deployed
Hosted on client's own server, domain, and infrastructure
★★★★★

“Sage was great. He understood the project and worked with me on my lack of knowledge on certain issues. He delivered my project on time and worked with me to fine tune little details. I'm excited to work with him and his team again in the future.”

— Nick Majersky, Founder, The Infinite Story Engine

Have a voice AI or real-time app idea?

We build and deploy AI systems end-to-end. Book a call to see what we can build for you.

Book a Discovery Call →More Case Studies