svg-voiced-video-studio: 60fps Voiced SVG Video & Multi-Platform Delivery Workshop
Transform scripts, storyboards, or verified cases into local personal voiceover with zero word swallowing + 4K 60fps native geometric SVG motion video + @2x four-size crop-safe covers + five-platform titles, descriptions, and pinned comments.
Key Invariants
- Inspect the script and voice environment first, then split sentences and synthesize with multi-pass caching. Based on: Chinese disyllabic rhythmic word theory, audience common ground theory, Grice's conversational maxims, and content-addressed idempotent construction. Before synthesis, always run lint_script.py to check: single-word officialese, binary reversal, five types of AI voice fingerprints (false empathy, false profundity, self-weighting, universal templates, triple parallelism), cold-open announcements, parentheses fillers, overly long breath gaps, sentence length coefficient of variation (
≥ 0.25), polyphonic characters, and number/English reading styles; for measured step-by-step content, retain audience-common measurement units (e.g.,token) and unify throughout, address objects and sources by real names, and converge selection chronologically; lock misread words using{pronunciation=>subtitle}or dual-trackttsText. The synthesis script supports--check-onlypre-check andout/.tts_cache/hash-based incremental continuation, physically splitting sentences at;:——(breath gap0.18s) and。!?(breath gap0.30s) with multi-pass best selection (the sole parameter source is in Voice & Script Craft Manual). - Reverse-drive the
60fpstimeline from measured seconds, with fast exits and reveal frames aligned to key points. Based on: normalized time parameterization and audiovisual synchronization perception window. The synthesis script writesscenesData.json; components must never hardcode frame numbers; springs useSPRING_PRESETSfour-tier unified for similar elements (mode C locks to no-bounce gear), exit0.25sfaster than entry; mask transitions userevealOn()to align reveal frames with emphasized words or cut points; Chinese on-screen text holds forminReadHoldSec()(chars÷4.5+1.5s, key digits≥ 2.5s). - Extract dual-state static frames for visual inspection first, then run full video encoding. Based on: defect detection shift-left and Gestalt figure-ground separation. For each scene, extract at
25%(entry state) and76%(text-heavy state); scenes with overlapping lines or trajectory crossings additionally extract at48%; confirm lines do not intersect text, paths are closed, text frame clearance≥ 8px, and at most 1 accent color focus per screen. - Generate all four cover sizes at once, strictly lock central
3:4safe zone for9:16. Based on: multi-viewport safe frame and mixed Chinese-Western visual character width norms. Cover main titles: pure Chinese characters≤ 6per line, mixed Chinese-Western visual character width≤ 6.2 em(unbreakable long proper nouns use--allow-7special approval up to7.2 emwith automatic font size reduction8%);9:16version top/bottom margin≥ 240px. - Copywriting must guard language and factual boundaries. Based on: expectation violation check and curse of knowledge. Pure text, zero formatting, remove quotation marks, Kuaishou max
4hashtags, forbid binary reversal sentences, forbid presenting hypothetical deductions as author's established facts, creator's fixed closing phrase preserved verbatim—detailed rules unified in Five-Platform Copy & Four-Size Cover Spec section 2, article 0; applies equally to narration and covers. - Philosophical/humanistic pieces: final scene preserves creator's fixed closing phrase verbatim.
With unceasing inquiry, find the living self; within limited consensus, achieve infinite possibilities.If already present in the submitted script, leave unchanged; when generating a script from a topic, default as the final scene closing; split at semicolon into two sentences for synthesis; leave4.5s~5.5ssilence after the final period. Pure commercial quick explainers follow workspace rules or user instructions. - Scenes dynamically expand/contract based on information points; visual aesthetics, data integrity, and Swiss layout follow the manual. Based on: Mayer's multimedia learning principles, Tufte's graphical honesty, and Swiss modular grid. Strictly forbid rigidly fitting or filling a fixed number of scenes: naturally split by "one core information point per scene" with complexity determining length (short commentary
3~5scenes, standard analysis5~9scenes, deep long-form10~16+scenes all freely scalable); data charts (unverified numbers never shown on screen, coordinates before data, bars start from 0, verify multipliers, source small text), horizontal 12 / vertical 6 column grid, and2~3anti-homogenization style signals per video, all follow SVG Motion Aesthetics Manual. - Final video must pass
-14 LUFStechnical inspection and independent blind review before delivery. Based on: ITU-R BS.1770 loudness standard and independent verification to prevent confirmation bias. Final mix adds percussion sound effects avoiding voice (sfx_synth.py), levels to-14.0 LUFS(true peak≤ -1.2 dBTP); after rendering, always run inspect_video.py to strictly check frame count, zero black frames, loudness, and true peak (unchecked items markedNOT_CHECKEDdo not count as pass); also execute independent blind review.
Visual Master & Canvas Mode Selection
Choose based on script style and primary publishing platform (if workspace AGENTS.md or user specifies colors, follow that):
| Mode | Logical Canvas → 4K Output (--scale=2) | Core Color Palette (zero gradients, 0px sharp corners) | Composition Preset | Cover Theme | Suitable Topics |
|---|---|---|---|---|---|
| A. Deep Charcoal Night Car Philosophical | 1920×1080 → 3840×2160 | Background #111110 · Main Ink #F2EFE9 · Accent #D94E28 | --preset long --speed 1.00 | --theme dark | Introspective analysis, existentialist long-form |
| B. Swiss Classic Warm Ledger | 1920×1080 → 3840×2160 | Background #F5F0E6 · Paper #FAF7F1 · Charcoal Ink #191715 · Wax Seal #C83E2B | --preset long --speed 1.00 | --theme vellum | Time & money ledgers, classical philosophy long-form |
| C. Swiss Warm Paper Media Vertical Quick Explainer | 1080×1920 → 2160×3840 | Background #F5F1EA · Paper #FAF8F3 · Ink Black #1A1A18 · Vermilion #D93B22 | --preset short --speed 1.07 | --theme editorial | Vertical business analysis, product reviews, real data short videos (scenes naturally expand/contract with information) |
Numbers use font-variant-numeric: lining-nums tabular-nums; forbid default old-style numeral fonts (e.g., Georgia).
Mode C Additional Notes: Shell passes theme={EDITORIAL_PAPER_THEME}; vertical canvas automatically switches platform obstruction safe zones (top ≥ 200px, bottom ≥ 400px, right ≥ 140px, single-line subtitles ≤ 16 characters); graphics only drawn within safe rectangle using swissGrid(safe) with 6-column grid; verify number reading list from lint output item by item.
Standard Five-Step Workflow
If the workspace AGENTS.md has manual review gates (topic, final script review), stop at the corresponding gate; do not render before approval:
- Pre-finalization internal blind review & decision recording: Before submitting the final script package, if the host supports sub-agents, first dispatch a sub-agent not involved in writing the script to check against the five AI voice types and factual boundaries, clean them up. The finalization package includes: "one-sentence core claim, mode and 2-3 chosen style signals (at least 1 breaking away from the most cliché version), voice and speed, scene-by-scene narration with
*keywords*and nine-column storyboard self-check, four-size cover text, five-platform titles" numbered item by item; after user approval, immediately write toout/定稿决策.md; subsequent rendering and cross-session handoffs treat this file as the sole source of truth.
Step 1: Script Inspection & Zero-Word-Swallowing Cached Voiceover Synthesis & Mixing
- Run
python scripts/lint_script.py <script_path>, clean up sentence structures, five AI voice types, and officialese single words; verify polyphonic character and number/English reading list; if readings are wrong, write{pronunciation=>original}. - Locate
gpt-sovits-studio/voice_profile.json(prefer running with.venv\Scripts\python.exededicated environment; first time add--check-onlyfor second-level pre-check of weights, CUDA, andffmpeg). For training new voice or encountering Windows memory errors, first read GPT-SoVITS Windows Single GPU Fine-Tuning Troubleshooting Guide. - Run synth_voiceover_template.py (select
--preset,--speed,--sfx auto; if containing English proper nouns or technical terms, add--asr-verify; already synthesized sentences automatically reuse viaout/.tts_cache/; full recalculation add--force-resynth). Outputs:public/audio/S01..SXX.mp3(for pure voice quality check),ambient_pad.mp3,sfx_bus.mp3,mixed_master_ducked.mp3(48kHz-14.0 LUFSvoice + ducked background music + avoided sound effects final master; the only audio track for the final video),src/data/scenesData.json,out/subfolder.srt,chapters.txtandsfx_cues.json. - For 1-2 key sentences, optionally add
"fx": "canyon" | "tape" | "water"(see voice_fx.py); before encoding video, must use multimodalread_fileto listen to eachpublic/audio/S01..SXX.mp3by ear (key check: English proper nouns and polyphonic characters have no blurry sounds, no skipped words; for pure Chinese fine-tuning, use{touken=>token}fortoken,{P D F=>PDF}forPDFto dual-track lock).
Step 2: Build Decoupled Remotion 60fps Native SVG Project
- If reusable
node_modulesexist, mount via Windows directory junction. - Copy motion_60fps.ts and SceneFrameShell_60fps.tsx, follow project conventions:
- Composition IDs: Main movie
MainEssay, scenesScene-S01…Scene-SXX; usetoShellTimeline()to convert timeline; - Audio track: only attach
audio/mixed_master_ducked.mp3once onMainEssayroot composition; keepplaySceneAudioshell closed; - All
interpolate()explicitlyclamp; uniformly useSPRING_PRESETS,EASE_SNAP / EASE_GLIDE / EASE_WHIP, default0.25sfast exit,revealOn()alignment,minReadHoldSec()hold duration, andswissGrid(safe)modular grid; - Aesthetic and data implementation use
accentAt()+mixHex()(red follows voice),cameraAt()(single canvas pan),taperStroke()/inkJitter()(modes A, B ink lines); commercial charts strictly follow aesthetics manual section 2 data standards.
- Composition IDs: Main movie
Step 3: Dual-State Sampling Inspection, -14 LUFS Programmatic Final Check & Independent Blind Review
npx tsc --noEmitzero type errors.- Run extract_keyframes_template.mjs to export key frames (default binds port
18123to avoid Windows Hyper-V/WinNAT reserved port range3000–3100), visually inspect for line-text intersections, gaps, orphans, and platform obstructions; then run audit_aesthetics.py to check red focus, element count, box lines, protagonist height, density variation, and font size hints. - Execute
npx remotion render … --scale=2 --codec=h264 --crf=16 --pixel-format=yuv420p --port=18123to directly render native true vector 4K60fpsfinal video (vertical2160×3840, horizontal3840×2160; completely eliminatesyuv420p4:2:0 chroma subsampling causing vermilion edge blur;studiopreview also uses--port=18123to avoidNo available ports found). - Always run inspect_video.py (pass
--expect-size 2160x3840[horizontal3840x2160],--expect-fps 60,--scenes-json src/data/scenesData.json), confirm 4K resolution, frame count, zero black frames,-14.0 ± 1.5 LUFSloudness, and≤ -1.0 dBTPtrue peak allPASS. - If the host supports sub-agents, hand over
qa_sheet.png,qa_phone.pngand "one thing the audience should remember" to an independent reviewer sub-agent who does not look at the code; receive back the most severe≤ 3issues with timestamps; fix and re-check before proceeding.
Step 4: Render @2x Four-Size Crop-Safe HD Cover Set
- Draft cover text according to Five-Platform Copy & Four-Size Cover Spec and pass three hard checks.
- Run render_4covers_template.py (choose
--themeper mode table) to output four.pngfiles, verify each has no single-character orphans and9:16text fully within central3:4safe frame.
Step 5: Deliver Pure Text Five-Platform Copy & Structured Acceptance Checklist
Output pure text, zero-format copy per spec section 2 (Bilibili timeline directly from out/chapters.txt; project records remain in out/, not mixed into delivery directory). Final reply provides clickable links to .mp4, .srt, four .png, copy .md, npm run studio preview and re-render commands, and a fixed brief delivery acceptance checklist (verified items, unverified items, design exception reasons).
Boundaries, Authorization & Stop Conditions
- Applicable Boundaries: For real-scene editing, live-person keying, or 3D realistic rendering requests, directly state that this Skill focuses on procedural native SVG voiced motion video and multi-platform packaging, not forcing templates.
- External Action Authorization: Default only generates files locally; without explicit user instruction, do not invoke browser or API to automatically upload/publish.
- Completion Acceptance Criteria: All hard-check items in
inspect_video.pymust bePASS(noFAILorNOT_CHECKED), all four-size covers and pure text five-platform copy are complete, and the acceptance checklist truthfully records the verification scope and exception explanations.