Image and video decision
Fliki
A narrow, useful text→video workflow (script → TTS → stitched royalty-free visuals → captions) is realistic for a single developer in ~30 hours using third-party TTS and stock APIs; reproducing Fliki's full catalog of voices, avatars, licensed media, and integrated models at scale is not practical without large vendor relationships and model/asset investments.
Visit website↗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.
What a replacement has to do
- Take a text script → generate TTS voiceover → pick/produce visuals → assemble timeline with captions and music → export rendered video file.
What it still won’t have
- Large catalog of licensed stock media bundled at scale
- Access to dozens-to-thousands of tuned proprietary voices and ultra-realistic voice clones
- Integrated, pre-tuned multimodal models and model catalog (many vendors)
- Branded, multi-avatar digital twin generation and managed avatar hosting
- Built-in enterprise features (team collaboration, branded templates, priority support)
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Fliki 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 minimal Fliki-like web service using Next.js (React) frontend and a Node.js + Express backend, store metadata in Postgres, and save assets on S3-compatible storage. Core features in scope: (1) web form to paste/upload a script or blog URL, (2) server-side TTS via a commercial TTS API (supporting 1–2 voices), (3) automatic selection of stock images or short royalty-free clips per sentence (via a stock-assets API or Unsplash/Pexels), (4) timeline composer that stitches clips, overlays generated audio and burned-in captions, and exports an MP4 (1080p) via ffmpeg, (5) simple credit/quota accounting and download page. Out of scope: building custom deep video models, many-language voice cloning, enterprise team features, and a full model catalog. Include retry/error handling for failed API calls, validation for uploads and text length, CI tests for core endpoints, and a README with deployment steps and infra IaC (Terraform or CloudFormation).
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 productFliki - official product page
- official docsFliki - Features
- official pricingFliki - Pricing
- open sourcecalesthio/OpenMontage
- open sourceHBAI-Ltd/Toonflow-app
Integrity checks
What held up, and what did not.
