Image and video decision

Autoshorts

A capable developer can build a limited AutoShorts clone (upload→auto-edit→publish) using open-source video tools and available models, but reproducing the product-grade polish, scale, integrations, templates, and operational reliability would be multi-week work and costly to match fully.

Visit website

Built by Alberto Ravasini ⚡, who ships 5 products in this index

You pay

$19/mo

$228/yr

Read off the official pricing page.

You’d pay instead

$100one-off58 h to build

$200/mo6 h/mo upkeep

On cash alone, building overtakes the subscription at 11 seats.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Autoshorts alternatives, with the arithmetic →

What a replacement has to do

  • Ingest source videos, automatically select and trim high-engagement clips, assemble vertical short (overlays/music/beat-sync), allow template edits and approvals, schedule and autopublish to socials.

What it still won’t have

  • Polished, battle-tested scheduling and cross-platform publishing reliability
  • Prebuilt viral templates and tuning optimized by product usage data
  • Priority support and onboarding
  • Edge-case media processing optimizations and scaling

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 11 seats.

Paid seatsseats

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal AutoShorts replacement using Node.js + Express, React, PostgreSQL, S3-compatible storage, ffmpeg for editing, and an LLM/vision API for clip scoring. Core features in scope: (1) authenticated upload and storage of source videos, (2) automated clip selection using an LLM/vision API that returns timestamps and scores, (3) ffmpeg-based assembly of 9:16 short videos with text overlays and music beat-sync per template, (4) web dashboard to preview drafts, edit overlays/timings, and approve, (5) scheduled autopublish workers that push videos to YouTube Shorts, Instagram Reels, and TikTok via OAuth and platform APIs, (6) simple billing gate (one paid plan). Out of scope: training custom models, multi-tenant enterprise SLAs, analytics beyond basic publish logs. Include error handling for upload/processing/publish failures, unit tests for the API and worker flows, and a docker-compose deployment for production-like testing.
How we checked3 sources · 2/3 runs agreed · evidence score 63

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 3 cited sources+3
  • Price verified on pricing page+3
  • Evidence score63

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 3

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded