This project has evolved from a podcast automation tool to a custom sleep story generation platform where users can create personalized bedtime stories.
- Customizable Story Generation: Users can optionally specify:
- Character name and age
- Character gender (with gender-neutral option)
- Companion animal and name
- Story location
- Values/morals to emphasize (courage, empathy, etc.)
- All fields have defaults if not specified
- Interactive Madlib Interface: Inline click-to-edit fields within story preview text with real-time updates
- Simple Payment Flow: $2 per story generation via Stripe MCP integration
- Real-time Progress Updates: GitHub Actions-style progress UI with polling
- SMS Notifications: Text message alerts when generation is complete (via Twilio)
- No Account Required: Simple, stateless transactions with token-based asset retrieval
- Frontend: Next.js with Tailwind CSS v3, TypeScript, and custom components
- Interactive inline editing with keyboard navigation
- Modern input styling with consistent 40px heights
- Custom dropdown styling overriding browser defaults
- Payment Processing: Stripe integration using Model Context Protocol (MCP) for semantic API interactions
- Database: Supabase for job tracking and progress state
- SMS Notifications: Twilio for completion notifications (international numbers, English only)
- Asset Storage: AWS S3 for persistent storage of generated audio, artwork, and metadata
- Real-time Updates: Polling-based progress tracking (every 2-3 seconds)
- Progress UI: GitHub Actions-style step indicator with elapsed time
- Error Handling: 3x retry mechanism with SMS fallback to customer service
- URLs: Human-readable progress URLs (e.g.,
/progress/2025-05-username-abc123) - Download Experience: Spotify-style media player with "Download All" zip functionality
- Story/script generation (OpenAI) - must complete first
- Metadata/title/description generation (OpenAI) - can run in parallel
- 8000 Artwork generation (OpenAI) - can run in parallel
- Audio generation (ElevenLabs TTS) - can run in parallel
- Enhanced MP3 creation with embedded artwork and metadata
- Asset storage in S3 with indefinite retention
scripts/generateEpisode.ts— Orchestrates the full episode generation (story, metadata, artwork prompt)scripts/generateMetadata.ts— Generates evocative, story-specific metadata and titlescripts/generateArtwork.ts— Generates artwork prompt for each episodescripts/generateAudio.ts— Generates TTS audio from the episode story
- After each script runs, assets are stored in the output directory
- Audio is uploaded to Vercel Blob and the blob URL is saved in the DB
- Metadata is inserted into the DB as a first-class object
- Local audio files are deleted after upload to save disk space
- All scripts use
export {};at the top to avoid block-scoped variable redeclaration errors - Run
tsc --noEmitto check type safety across all scripts - If you see TS2451 errors, ensure each script starts with
export {};
See IMPLEMENTATION_PLAN.md for the detailed development roadmap and branch strategy.
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun devOpen http://localhost:3000 with your browser to see the result.
You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.
This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.
To learn more about Next.js, take a look at the following resources:
- Next.js Documentation - learn about Next.js features and API.
- Learn Next.js - an interactive Next.js tutorial.
You can check out the Next.js GitHub repository - your feedback and contributions are welcome!
The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.
Check out our Next.js deployment documentation for more details.