Single SourceStudios Engage SSS
Documentary video factory

A pipeline that turns a topic into a fully scored, narrated documentary, end to end.

StoryForge takes a subject, researches it, writes a script, generates narration and visuals, and renders a finished video with a mastered audio track, all without a human touching an editing timeline.

Two rendering stacks, v1 and v2
-16 LUFS mastered audio
$0 hero motion, no paid API
What it is

A multi-project factory, not a single video tool.

Each documentary lives in its own project folder with its own config, assets, and script. The engine runs every project through the same eight-stage pipeline: trend discovery, research, script generation, asset scraping, narration, composition, render, and mastering.

Two stacks, one switch

An environment variable picks between two complete, independently working rendering stacks. Neither was deleted when the other was built; both still run.

Real research, not a template fill

Topics are validated and researched against live web sources before a script is written, with a fallback chain if the primary research provider is unavailable.

Rendering stacks

v2 is the default. v1 is the proven fallback.

Selected per run by the STORYFORGE_STACK environment variable. Both stacks' files coexist in the repo; nothing was removed during the migration to v2.

v2, default

HTML + GSAP, local TTS

  • Composition: HTML plus a paused GSAP timeline, rendered via HyperFrames
  • Narration: Kokoro-82M, running locally, no per-video API cost
  • Research: Tinyfish primary, Tavily as fallback
  • Output: a single composition per project, no composition ID needed
v1, fallback

Remotion, cloud TTS

  • Composition: Remotion, React-based scene composition
  • Narration: Chatterbox, running on Modal
  • Research: Tavily primary, Google Custom Search as fallback
  • Output: a Root.tsx composition, the historical baseline
The pipeline

Eight stages, topic to mastered file.

Every project runs the same sequence. The v2 multi-part render splits long documents into one composition per part, then concatenates with ffmpeg, which fixes a decode-load hang that affected earlier long-form runs.

00
Trend discovery
01
Research
03
Script generation
04
Asset scraping
05
Narration + captions
06
Composition build
07
Render
08
Master + loudness audit
Recent build

Free 2.5D hero motion, no paid image-to-video API.

The default hero-clip provider now generates depth-based parallax motion from a still image, running a depth model and a WebGL2 shader inside a headless browser, entirely on local compute.

$0
cost per hero clip
509 files
changed in the commit that shipped this provider
-16
LUFS mastering target, audited every render
Where it stands

Mid quality rebuild, one paid dependency dropped for good.

The project is mid-way through a visual quality push. A previous paid image-to-video provider was dropped permanently after its account balance was exhausted with no top-up; the replacement free provider is now the shipped default.

Shipped
Depth-parallax hero motion, default provider

A dispatch table lets the asset stage swap image-to-video providers without touching the rest of the pipeline. The free provider is now the default; a second provider exists but is dormant and unverified.

Shipped
Style-lock and claim-grounding, same commit

The commit that shipped the free depth-parallax provider landed 509 files at once: a style-lock module fixing the visual language across generated stills, and a claim-grounding gate checking narration against the research digest.

Retired
Paid image-to-video provider, dropped permanently

Account balance exhausted mid-run with no further funding; kept in the codebase only as a reference implementation, not an active path.

Next
Higgsfield i2v provider, pending API key

A second image-to-video provider was built and wired into the dispatch table but left dormant, waiting on an API key before it can run as an alternative to the free depth-parallax default.

Topic in, mastered documentary out.

Two working rendering stacks, a research-backed script pipeline, and hero motion plus narration that run locally at no per-video cost.

Active development
Evidence stamp

Evidence: compiled from the storyforge repository on 2026-08-03. Every number on this page traces to a file path or command output in the source tree. Last updated: 2026-08-03.

Single Source

Every number on the dossier and whitepaper pages traces to a file path or command output in the source tree.

LinkedIn Facebook (c) 2026 Single Source Studios (Pty) Ltd