Kill the Grind, Keep the Magic: How We Used AI Ethically to Turn 200+ Hours of D&D Into a Living Universe

The Critical Distinction

Before anything else, we need to be clear about what ethical AI use in creative production looks like, and what it does not. Ethical AI is not writing your story for you. It is not inventing lore that doesn't exist. It is not replacing the creator's voice or making creative decisions. What it is doing: extracting what you already created, organizing it into a universe bible, correcting what machines mangled, and making it searchable and reusable.

This distinction guided every decision we made in building the pipeline. The creators spoke every word. The GM built every world detail. The players made every choice. AI processed the volume. Humans ensured the quality. At no point did the system generate fiction, invent characters, or make narrative decisions. It listened to what was already there and organized it so nothing would be lost.

Your Content Is Trapped

Gold, Green and Red is an 88-episode live-play D&D campaign spanning three years and 200+ hours of improvised storytelling. Six to eight players plus a GM, every session different, lore generated organically across hundreds of hours. None of it was written down. The entire world existed in YouTube recordings and the memories of the people at the table.

Character names were mangled in every auto-caption. YouTube achieved only 38% speaker attribution: "Juramentum" became "Gerimentum," "Merick" became "America," "Quaylithon" became "Queen Lathon." Manual processing at the old rate required 2.5 to 3.5 hours per episode. For 88 episodes, that meant 220 to 308 hours of human labor.

From Raw Content to Source of Truth

The pipeline we built chains four tools into a nine-step repeatable workflow. AI extracts and organizes what creators already built. One source of truth then feeds every format your audience touches: the Universe Hub, the World Setting Book, draft animation scripts, episode summaries, fan-facing content. Same canon, same spelling, same truth, different formats for different audiences.

Steps 1–2: Acquisition and Transcription

Each episode is downloaded from YouTube using yt-dlp. The MP4 is submitted to AssemblyAI's transcription engine with speaker diarization enabled. For a typical three-hour episode with eight distinct voices, the engine produces 1,200 to 1,900 attributed utterance blocks. Cost: $0.51 per episode.

Step 3: Speaker Mapping (Human Gate)

This is the most critical gate in the entire pipeline. AI proposes a speaker map based on evidence. The human confirms, corrects, or flags. This takes approximately two minutes per episode. No downstream deliverable works if this step is wrong, so a human does it every time.

Step 4: AI Processing

With validated speaker mapping, Claude processes each transcript through multiple parallel passes. Every utterance is classified into one of eight content types. A canonical spelling dictionary with 200+ correction patterns is applied automatically. The OOC classifier started at a 27% false positive rate and improved to 0% through iterative learning.

Steps 5–6: Validation and Lore Bible (Human Gates)

Every OOC-flagged block is reviewed by the human validator. Every lore discovery is cross-referenced against the Master Lore Bible. The Bible evolved through nine major versions, growing into a 108KB, 13-section world-setting reference: 88 NPCs, 14 deities, 63 locations, 171 lore entries, 75 journal entries, and 200+ spelling correction patterns.

Steps 7–8: Universe Hub and Summaries

The Universe Hub is the fan-facing output: an interactive universe compendium that opens in any browser. 88 NPCs, 171 lore entries, 63 locations, 75 journals, 88 episode pages. Narrative summaries are written for all 86 episodes — not recaps, but original prose capturing the emotional weight of each session.

Step 9: The Correction Cascade

When new canonical information is confirmed, corrections cascade backwards through every previously processed file. The project executed 567 retroactive corrections across 165 files in a single automated pass. The digital-first approach means the entire corpus improves as knowledge grows.

AI Proposes. Human Decides.

Three human gates in every episode. Speaker mapping, OOC validation, lore arbitration. Approximately 5 to 7 minutes of human work per episode. Everything else is automated. But those 5 to 7 minutes are where creative authority lives.

The Compounding Effect

Raw recordings became a Master Lore Bible. The Bible became a 176-page, 48,000-word World Setting Book, written in days instead of months. The transcripts became 42 draft animation scripts representing 126 hours of production-ready dialogue. Without the pipeline, producing all of these outputs manually would require approximately 1,200 hours of human labor.

Start This Weekend

You do not need to be a developer. You do not need to surrender creative authority. Pick three episodes. Download them with yt-dlp (free). Transcribe with AssemblyAI ($50 free tier). Validate speaker maps: two minutes each. Process with Claude. Start your Bible. Even v1.0 is better than zero. The full framework and live walkthrough will be presented at GenCon 2026.

AI does not replace the creator. It kills the grind. And keeps the magic.