Skip to main content

Video pipeline

Long uploads become ranked clips and platform-ready files through a staged pipeline. Exact task names and retries live in the application code; this page is the conceptual map.

Stages

  1. Ingest — upload or URL import; media lands in object storage; a video row is created.
  2. Transcription — speech-to-text (Whisper-class) produces segments used everywhere downstream.
  3. Scoring — multi-signal highlight detection (LLM, audio, scene, mood, hooks, chat, trends, loudness, and optional vision signals). See the public Signals section on this site for the product framing.
  4. Director & style — auto-direction (zoom, reframe, pacing) and caption presets interpreted into render parameters.
  5. Render — FFmpeg with allow-listed arguments; plugins can hook pre/post render.
  6. Publish — scheduled or immediate posts to linked social accounts with idempotent retries.
  7. Analytics — per-platform metrics roll up for feedback loops.

Async execution

Heavy stages run on Celery workers. Progress streams to the UI via realtime channels.