[verdict][curated prompt][source: socialfaktory.com]
Can I vibecode SocialFaktory?
// buildable in a weekend, but real gaps stay open
The generation half is honest API glue: script writing is an LLM call and the video itself comes from hosted model APIs (fal.ai and friends), so a personal brief-to-video pipeline is very buildable · but you pay those per-generation model invoices yourself either way. The publishing half is the same wall every scheduler hits: TikTok, Instagram, and YouTube OAuth apps are review-gated for weeks, which is why SocialFaktory itself publishes through Postiz. The honest DIY is a generation script feeding a self-hosted Postiz, and what's left over is the tuned prompt pipelines, the QA pass, and someone else eating the platform-review pain.
confidence: high
what it is: Turns a text brief into a finished short video with AI actors and voices, then posts it to your social channels
Buildability index · an editorial game
- Price 49 $/month weight: plus 3
- Time multi-day weight: plus 1
- Category social media no weight
- Moat integrations · execution quality weight: minus 2
- Confidence high weight: plus 1
- What you lose 5 items weight: minus 2
- Site socialfaktory.com (si apre in una nuova scheda) no weight
They cancel out. This is where it comes down to how much the subscription annoys you.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Turn a text brief into a script and a rendered short video via hosted AI model APIs, then queue and publish it through a self-hosted Postiz.
what you need
- Anthropic or OpenAI API key for scripts
- video-generation API key (fal.ai or similar)
- self-hosted Postiz for the platform OAuth and publishing
- always-on box
Submitted by the founder · the publishing half really is Postiz under the hood, so start there.
The prompt
A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.
Build me a personal AI video factory to replace SocialFaktory. Requirements:
- Node + Express + better-sqlite3; a localhost dashboard with a brief form
(topic, tone, target duration) and a queue of generated videos.
- Script step: send the brief to the Anthropic API and get back a hook line,
a spoken script, and a visual prompt; keep the system prompt in
prompts/script.txt so I can tune it without touching code.
- Video step: submit the visual prompt to fal.ai's queue API for a
text-to-video model with native audio, poll until done, download the mp4
into media/ and record the actual dollar cost per generation in the DB.
- Review page: each finished video gets a player plus approve, regenerate,
and discard buttons; nothing publishes without an explicit approve.
- Publish step: on approve, POST the video and caption to my self-hosted
Postiz via its public API (POSTIZ_URL and POSTIZ_API_KEY in .env) with a
scheduled time · Postiz owns the platform OAuth; never call TikTok,
Instagram, or YouTube APIs directly.
- A node-cron tick retries failed generations 3 times with backoff and marks
rows before submitting so nothing ever double-bills.
- A running-costs box on the dashboard summing this month's model spend.
- Out of scope: multi-brand workspaces, teams, analytics, auto-QA, and any
direct platform integrations (say so in the README).
- README: getting the two API keys, pointing at a Postiz instance, and what
a single video roughly costs to generate.Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.
What you lose
- pre-approved platform OAuth apps (TikTok/Instagram/YouTube reviews take weeks)
- prompt pipelines tuned per model, format, and tone
- an automated QA pass before anything ships
- multi-brand workspaces and a scheduling calendar
- a flat bill · DIY pays every model invoice directly, and video models are not cheap
Why people still pay
Video model APIs churn monthly (pricing, quality, aspect-ratio quirks, content filters) and social platforms churn their publishing rules just as fast; the subscription outsources both treadmills. The flat price also converts unpredictable per-second video generation invoices into one known number, and the platform OAuth apps arrive pre-approved instead of after weeks of app review.
moat: Integrations Execution quality what a moat is
platform-review pain + tuned generation pipelines
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- Postiz (opens in a new tab) — Open-source social publishing · the scheduling/OAuth half of this product, self-hostable.
- Mixpost (opens in a new tab) — Self-hosted social media management, an alternative publishing backbone.
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
