Image and video decision
Shortgram
A competent technical user can build a useful, narrower self-hosted short-video automation pipeline (script → ffmpeg assembly → TTS → upload), but reproducing the full commercial product (polish, multi-platform reliability, analytics, and UX) is substantial and benefits from the open-source projects cited rather than reimplementing everything from scratch.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off48 h to build
$300/mo6 h/mo upkeep
No published price to break even against.
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 Shortgram alternatives, with the arithmetic →
What a replacement has to do
- Ingest a prompt or source media → generate short-video script/shot list with an LLM → assemble clips and assets into a timeline with ffmpeg + templates → synthesize voiceover and burn captions → render/export and schedule/upload to platforms via their APIs
What it still won’t have
- Hosted UI, onboarding and product polish (dashboard, templates marketplace)
- Built-in multi-platform analytics and insights
- Maintained integrations and automated reliability/backoff for platform rate limits
- Commercial support, uptime SLAs, and legal/compliance handled by vendor
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Shortgram 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
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
Build a self-hosted AI short-video automation service using Node.js + Express backend, PostgreSQL, ffmpeg (in Docker), and OpenAI (or compatible) for LLM tasks; use an off-the-shelf TTS provider (e.g., Amazon Polly or ElevenLabs) and store assets on S3-compatible storage. Core features in scope: 1) API to accept prompt or source media, 2) LLM-driven script/shot-list generation, 3) ffmpeg templates to assemble/cut clips and overlay captions, 4) TTS voiceover and subtitle burn-in, 5) render/export to target platform specs, 6) a scheduler to upload via YouTube/TikTok APIs with retries and basic per-platform rate-limit handling, 7) minimal web UI for queue/status and manual overrides, plus tests for the pipeline and error handling. Out of scope: template marketplace, multi-user billing, analytics dashboards, and native mobile apps.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 5 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score64
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 · 5
Every page the run actually retrieved.
- official productShortgram – AI Faceless Channel Automation for YouTube Shorts, TikTok & Reels
- open sourceharry0703/MoneyPrinterTurbo
- open sourceHao0321/video-autopilot-kit
- open sourceRayVentura/ShortGPT
- open sourceYILS-LIN/short-video-factory
Integrity checks
What held up, and what did not.
