Six months ago I started Keyvello (keyvello.com) — an AI video generator that turns a prompt into a complete short-form video in 2–5 minutes. Here's the technical breakdown for fellow builders. The problem Faceless creators on TikTok / YouTube Shorts / Reels spend 2–4 hours per video on scripting, voiceovers, B-roll, captions, and editing. Most burn out before they post 10 videos. The stack #
Frontend: Next.js 16, React 19, TypeScript, Tailwind CSS 4, Radix UI #
Backend: Next.js API Routes (App Router) #
DB: Supabase (Postgres + Auth + RLS) #
AI: GPT-5.5 for scripts, Fal.ai for images, ElevenLabs for voices #
Video: FFmpeg via fluent-ffmpeg , Sharp for image processing #
Storage: Cloudflare R2 (S3-compatible) #
Payments: Dodo Payments #
Compute: Vercel for the app, Modal for the video pipelines #
State: Zustand The pipeline prompt → GPT-4o script → scene splitter → parallel(Flux images + ElevenLabs audio) → FFmpeg composition (Modal) → R2 upload → status update What surprised me #
Modal beats running FFmpeg in Vercel. Cold starts on Vercel functions made 60s+ videos impossible. Modal webhooks solved it. #
RLS is non-negotiable from day one. Retro-fitting row-level security at 1K users is painful. #
Credit refunds need their own RPC. I hit a silent failure with increment_user_credits getting blocked by a trigger. Use add_credits instead. #
Users want templates, not raw control. I shipped a "blank canvas" mode early. Nobody used it. The 11 named templates (AI Stories, Fake Texts, Stick Animation, etc.) do 95% of generations. What's next Better lipsync for the talking-avatar templates. Tighter cost controls per template tier. Affiliate program. If you're building something in AI video, would love to compare notes — drop a comment.
source & further reading
dev.to — original article
Your AI Agent's Logs Are Lying to You: A 4-Field Schema That Actually Works
I Was Skeptical of AI. Then It Saved Me Hours of Writing.
Tired of re-recording my README demo GIF by hand, I turned the whole demo environment into code