Find your direction by making things
Chapters & sources
Production record
Optional captions use measured narration blocks with approximate sentence timing. Audio was measured, not listened to.
| Output | 239.167 s · 1920 × 1080 native · 30 fps · 7175 frames · no upscaling |
|---|---|
| File | MP4 · H.264 High · yuv420p · AAC 48000 Hz stereo · 11,012,292 bytes (10.50 MiB) |
| Elapsed | 1918.367 s from 2026-10-27T17:03:16.893244+00:00 to 2026-10-27T17:35:15.260469+00:00; narration/asset preparation through final render and reader verification, including authoring/review. Excludes prior book reading/writing and later packaging. |
| Render processing | One successful job · 195.459 s process wall time · internal pipeline 194.082 s. Not pure GPU compute time. |
| Render stages | compile: 0.207 s · browser_probe: 0.059 s · video_extract: 0.000 s · audio_process: 2.319 s · file_server: 0.002 s · capture_disk: 181.592 s · encode: 9.395 s · assemble: 0.456 s |
| Animation | Authored SVG/GSAP 3.15.0 · HyperFrames 0.8.200 · Node 24.20.0 · two software Chromium capture workers · no generative video model or GPU encoder |
| Narration | Local synthetic Kokoro v1.0 82M ONNX · bm_george · en-gb · speed 1.0 · CPUExecutionProvider, four threads · kokoro-onnx 0.4.7 / ONNX Runtime 1.30.0 · 24 kHz mono PCM16 source. Quantization unverified; model SHA-256 and bytes saved; no adapters or exposed seed. |
| Voice generation | 14 successful paragraph jobs · 0 failed/retried · 43.575 s elapsed · 42.831 s summed inference calls |
| Music and effects | Original procedural DSP · seed 27102026 · 16 cues · 48 kHz stereo stems · 7.148 s successful audio preparation · 0 failed/retried |
| Audio | Finished mix -15.06 LUFS integrated, -1.57 dBTP, 2.70 LU range · voice target −18 LUFS, score target −36 LUFS · measured, not auditioned |
| Settings | Delivery quality, 30 fps, software capture. No upscaling, interpolation or ComfyUI jobs. Diffusion steps, sampler, scheduler, guidance, denoise and adapters do not apply to authored vector animation. |
| Resources | CPU narration and software browser capture. Peak VRAM and energy not recorded. |
| Verification | Full decode passed; 10 decoded frames visually checked; zero validation/layout/runtime errors. 20 intentional narration/reading-hold warnings. Captions use measured paragraphs with approximate sentence timing. |
| Scene 1 timing | 33.003 s output · 5.887 s voice generation. Separate scene render time not exposed. |
| Scene 2 timing | 33.067 s output · 5.669 s voice generation. Separate scene render time not exposed. |
| Scene 3 timing | 31.808 s output · 5.606 s voice generation. Separate scene render time not exposed. |
| Scene 4 timing | 35.541 s output · 6.398 s voice generation. Separate scene render time not exposed. |
| Scene 5 timing | 34.048 s output · 6.343 s voice generation. Separate scene render time not exposed. |
| Scene 6 timing | 35.563 s output · 6.537 s voice generation. Separate scene render time not exposed. |
| Scene 7 timing | 36.128 s output · 6.392 s voice generation. Separate scene render time not exposed. |