Thoughts

ENN Pipeline Session 36 (2026-03-24): First end-to-end short produced and reviewed. Key learnings and decisions: PRODUCTION SPECS LOCKED: - YouTube Shorts target: 40-60 seconds (100-150 word voiceover) - Visual plan per short: 5-7 Flux stills, 1-2 Hailuo video clips (5s each), 3-4 avatar shots - Hedra now generates 2-3 chunks per short with rotating framings (Close > Medium > Wide). Audio split via ffmpeg, separate Hedra generation per chunk. hedra_chunks.json tells Remotion which clip to use at what offset. - Cost per short estimate: ~$3.20-6.44 (Hedra is 90%+ of cost, monitoring credits for real baseline) - NewsTicker component renders on both YouTube and TikTok with platform-specific CTA BUGS FIXED THIS SESSION: - Hedra portrait paths updated from pre-rebrand (hedra_01/02/03.png) to post-rebrand (Desk_Anchor_Front_-_{Close,Medium,Wide}.png) - flux_asset_library.short_id FK made DEFERRABLE, registerAsset checks if short exists before referencing - render-batch asset filter now excludes both final.mp4 and tiktok.mp4 - Remotion redeployed to Railway (was stale, missing ticker) PIPELINE STATUS: Test short "Monks Hacking the Anti-Gravity Field" (Mantis, score 87>92) needs re-render with corrected specs (was 74.9s, needs trimming). 19 scripts from 2 Google Drive docs (religion-fae + nuclear batches) pending processing. Railway Remotion deploy triggered end of session. FUTURE: Build a /process-scripts slash command that auto-searches Drive for new Gemini exports. Could also run as scheduled task so nothing gets missed as long as Dave uploads to Docs from Gemini.

UFO UAP RV YT Pipeline: Phase 2 complete. 42 production-ready JSON manifests across 4 batches (Nuclear Facilities Gem A: 16, Nuclear Facilities Gem B: 9, Religious Experiences Gem B: 9, Religious Experiences Gem A: 8). All scripts graded A. 3 faceless narrator voices created via ElevenLabs Voice Design v3 (Dark Doc, Hushed, Elder) with rotating assignment across faceless scripts. Character bible updated with full Faceless section. Process-scripts skill fully operational. Ready for Phase 3: ElevenLabs voiceover generation + Whisper word-level timestamps. Cost estimates: fal.ai ~$5-7 for full batch Flux images, ElevenLabs and Hedra pull from subscription plans, Luma is per-generation API credits. Next session starts Phase 3.

UFO UAP RV YT Pipeline - Phase 2 Complete (Session 15, March 19 2026). 42 production-ready manifests across 4 batches covering Nuclear Facilities and Religious Experiences. 3 faceless narrator voices selected and saved to ElevenLabs (Dark Doc, Hushed, Elder - rotating across faceless scripts). All scripts graded A with visual plans, character casting, and voice assignments locked. Phase 3 (ElevenLabs voiceover generation + Whisper word-level timestamps) is next. May want a 3rd Gemini topic session to round out content mix toward the ~75 pre-launch target.