The Problem
Parents struggle to find time to create unique, engaging bedtime stories for their children every night. Traditional audiobooks lack personalization and the parent's own voice.
The Solution
StoryEcho uses AI to generate custom stories, images (SDXL / GPT-4.1), and voice narration using TTS voice cloning technology.
Tech Stack
Next.js
React
Capacitor
Supabase
Cloudflare R2
OpenAI
TTS
SDXL
Architecture & Implementation
- Next.js web app with TypeScript
- Capacitor mobile app for iOS/Android
- OpenAI GPT-4.1 for story generation
- SDXL for image generation
- TTS for voice cloning
- Supabase for auth, audio, image and metadata storage
- Cloudflare R2 for media storage
Key Features
- Voice cloning using TTS
- Story + image generation (SDXL / GPT-4.1)
- Next.js web app + Capacitor mobile app
- Supabase for auth, audio, image and metadata storage
- Personalised stories with custom themes
- Parent-voice narration