Image and video decision

StoryShort

A competent developer can build a useful minimal replacement in ~30 hours using existing models and ffmpeg; StoryShort does not show durable moats in the supplied page.

Visit website
SubscriptionCustom pricing
Initial build30 hours
Monthly upkeep6 hours + $50
Evidence3/3 runs agree

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 StoryShort alternatives, with the arithmetic →

What a replacement has to do

  • User supplies topic or script prompt → generate short vertical video (visuals, voiceover, captions) → export MP4 for TikTok/YouTube Shorts

What it still won’t have

  • Polish, UX and reliability of a commercial product
  • Large-scale content moderation and safety tuning
  • Any proprietary, curated content or in-house models the vendor may use
  • Built-in platform integrations and analytics the SaaS may provide

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

StoryShort does not publish a price we could read, so there is nothing to compare against. What building costs is below.

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 self-hosted AI faceless short-video generator as a web app using FastAPI (Python) backend, React frontend, Postgres for job metadata, S3-compatible object storage, and ffmpeg for video assembly. Core features in scope: accept a topic prompt and target duration; generate a short script/shot list using an LLM API (or LocalAI); generate TTS voiceover for each shot; create or retrieve visuals per shot (simple stock fetch + optional image generation via diffusion model); assemble vertical 9:16 MP4 with synchronized audio and burned captions using ffmpeg; provide downloadable MP4 and a webhook/endpoint for optional upload. Out of scope: native mobile apps, multi-language localization, a paid billing system, and training proprietary models. Include error handling, background job retries, logs, and unit tests for the API and video-assembly pipeline.
How we checked3 sources · 3/3 runs agreed · evidence score 90

How the score was reached

  • Build verdict base78
  • An open-source build was found+5
  • 3 cited sources+3
  • 3/3 assessment runs agreed+4
  • Evidence score90

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.

✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded