How We Built a Full SaaS in 24 Hours with Claude, Next.js, and Supabase
From concept to live product — with AI debriefs, audio generation, payments, podcast search across 4.5M+ shows, and 12 pages — in a single day. Here's exactly how.
The Challenge
We wanted to test whether AI-assisted development could take a product from idea to live, paying-ready SaaS in 24 hours. Not a landing page. Not a prototype. A real product with:
- • Full authentication (email and magic links)
- • AI-powered content pipeline (transcription → analysis → audio)
- • Payment integration with real payment processor
- • Interactive audio player with highlights, chapters, search
- • 4.5M+ podcast catalog with real-time search
- • Email system, admin dashboard, legal pages, blog
- • Custom domain, CDN, and email delivery
The Timeline
Concept & Architecture
Discussed podcast summarizer ideas, researched competitors (Snipd, Podwise, Castmagic), mapped out the stack. Decided: Next.js 16 + Supabase + Cloudflare R2 + Vercel.
Database & Backend
Designed 8 Supabase tables with RLS policies, auth triggers, and tier enforcement. Built the worker pipeline: PodcastIndex → YouTube/Whisper transcription → Claude analysis → TTS audio → R2 storage.
First Debrief Generated
End-to-end pipeline test: All-In Podcast E261 → 100MB audio → 8 Whisper chunks → 71K char transcript → Claude debrief with 7 takeaways and 6 quotes → TTS audio on R2. Cost: $0.65.
Frontend MVP
Landing page, auth (email + magic link), dashboard with podcast search, debrief viewer, pricing page. All in Next.js 16 with Tailwind CSS v4.
Payments & Polish
Stripe payment integration, admin dashboard, explore page (4.5M+ podcasts), episode intelligence (interactive highlights, chapters, keyword search), about page.
Domain, Email & Deploy
Bought poddebrief.com, configured DNS on Cloudflare, set up Resend for transactional emails, deployed to Vercel, Supabase SMTP configured, custom auth emails.
Audio CDN, Podcast Show & Blog
Cloudflare Worker for R2 audio delivery, generated PodDebrief Weekly Episode 1 (~20 min), RSS feed, legal pages, blog. Switched TTS from ElevenLabs to OpenAI (90% savings).
The Stack
| Service | Role | Cost/ep |
|---|---|---|
| Claude Sonnet 4.6 | AI debrief generation + episode intelligence | ~$0.22/ep |
| Next.js 16 | Full-stack frontend (App Router, React Server Components) | — |
| Supabase | Database, auth, RLS, real-time | Free tier |
| Vercel | Frontend hosting, serverless API routes | Free tier |
| Cloudflare R2 + Workers | Audio storage + CDN | Free tier |
| OpenAI Whisper | Audio transcription (when YouTube unavailable) | $0.10/ep |
| OpenAI TTS (tts-1) | Audio debrief generation | $0.029/ep |
| PodcastIndex API | Podcast catalog (4.5M+ shows) | Free |
| Stripe | Payments (integrated, switched off during the free beta) | Transaction fees |
| Resend | Transactional email (magic links, digests) | Free tier |
Total cost per debrief: ~€0.35. Fixed monthly costs: ~€43 (at scale with Vercel Pro). Most services on free tier during launch.
The AI Pipeline
The core magic is the debrief pipeline. When a new episode drops on any podcast you subscribe to, here's what happens:
Detect — PodcastIndex API alerts us to new episodes
Transcribe — Try YouTube transcript (free when available) → fall back to OpenAI Whisper with ffmpeg chunking for large files
Analyze — Claude Sonnet 4.6 generates structured debrief: takeaways, quotes, predictions, action items, links
Intelligence — Second Claude pass extracts highlights (8 categories), chapters, keywords
Voice — OpenAI TTS converts the debrief to audio (auto-chunked at 4096 chars)
Deliver — Audio to Cloudflare R2, debrief to Supabase, notification to user via email + RSS
Lessons Learned
1. AI doesn't replace architecture decisions
Claude wrote most of the code, but the hard decisions — Supabase vs. Postgres, R2 vs. S3, Supabase vs. Firebase, volume-only pricing — still required human judgment. AI accelerates execution, not strategy.
2. YouTube transcripts cut our transcription costs
Many popular podcasts publish on YouTube. We always try the free YouTube transcript first and only pay for transcription when there is none.
3. OpenAI TTS is 90% cheaper than ElevenLabs for this use case
We started with ElevenLabs ($0.30/debrief) and switched to OpenAI tts-1 ($0.029/debrief). For informational audio, quality difference is negligible.
4. Vercel serverless can't do everything
We hit issues with aws4fetch for R2 signed requests on Vercel's serverless runtime. Solution: Cloudflare Worker with R2 binding — faster, simpler, and free tier covers our usage.
5. "Same features. Just more." is the simplest pricing strategy
Every tier gets every feature. The only difference is volume (5/50/200 debriefs per month). No feature gates, no confusion, no "but I can't do X on the free plan" complaints.
What's Next
We shipped the product. Now comes the hard part: getting users. Our roadmap includes PodDebrief Weekly on all podcast directories, a weekly newsletter, Notion export, and eventually a mobile app. But the core product — AI debriefs with interactive highlights — is live and free to try.
Try PodDebrief Free
The product we built in 24 hours. 5 free debriefs per month. All features. No credit card.
Start for free →