Project 13 / Generative media
Automated UGC Video Pipeline
Turns a marketing brief into a structured, approved and cost-tracked vertical video render job.
01 / Problem
AI video generation becomes expensive and fragile when scripts, licensing, asynchronous renders and retries are handled manually.
02 / System
Designed as a controlled operational pipeline.
A provider-neutral orchestration layer generates emotion-mapped scripts, enforces consent and approval, tracks asynchronous render state and assembles branded output.
Three reusable briefs queued
9:16 output contract
Per-stage cost records
03 / Reliability controls
What keeps the system honest.
04 / Verification
Actual n8n webhook
Actual n8n webhook queued three renders and verified replay, approval, consent and cost controls. Included MP4s are synthetic assembly proofs, not vendor avatar output.
This is a locally verified engineering demonstration using synthetic data and controlled service adapters. It is not described as a production client deployment unless live evidence is added later.
Inspect the implementation.
Sanitized exports and test artifacts from this demonstration. No credentials or client data are included.
Brief-to-script, approval and render queue.
Open file JSONRender callback workflowAsynchronous completion and failure states.
Open file JSONReusable brief fixturesThree product-independent input examples.
Open file MDProvider researchQuality, API, consent and portability tradeoffs.
Open file MDUnit economicsTransparent cost model by monthly volume.
Open file JSONMachine-readable executionQueue, replay, consent and cost assertions.
Open fileCompleted outputs
Three reusable render proofs.
These short MP4s verify vertical assembly, captions and branding. They use synthetic media and are not presented as third-party avatar output.