Timestamped Voice-Over Image Pack Generator
Turn a timed voice-over transcript into style-locked images, one per beat, generated and named in order, with a hold-time manifest.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a good idea for a faceless video. You could generate images based on the script content. It would probably help to break the script into segments first and then describe what each image should show. I can help you think through what visuals would work for each part.
TIMESTAMPED IMAGE PACK OUTPUT INPUT • Script: 240-second voiceover on productivity habits • Niche: Productivity / business advice • Style: Minimalist line drawings (MS Paint aesthetic) • Aspect ratio: 16:9 (YouTube) • Resolution: 1920x1080 GENERATED FILES (20 images, 12-second intervals) 0.00.png → "5 habits of productive people" (title card, simple frame) 0.12.png → Person at desk, coffee mug, clock 0.24.png → Checklist with 3 items 0.36.png → Brain diagram, light bulb 0.48.png → Calendar view, X marks on days 1.00.png → Phone on desk, crossed out (distraction) 1.12.png → Morning routine icons (7am, exercise, shower) 1.24.png → Deep work - person with headphones 1.36.png → Time blocks (color-coded) 1.48.png → Energy chart (high/low throughout day) 2.00.png → Batch processing illustration 2.12.png → Meeting room with 3 people 2.24.png → Notes on whiteboard 2.36.png → Break time - person stretching 2.48.png → Nutrition: plate of food 3.00.png → Sleep: person in bed, zzz 3.12.png → Weekly planning - 7-day grid 3.24.png → Recap checklist (5 habits listed) 3.36.png → Call to action text 3.48.png → Your logo + social handles (end card) DOWNLOAD: All 20 files auto-named by timestamp, ready for drag-and-drop into CapCut/Premiere. Timeline placement: each image holds for 12 seconds. STYLE LOCK REFERENCE: Consistent pen weight (2px), palette (3 colors), and layout spacing across all 20 images.
About this skill
Your voice-over is done. Now you need 40 images that match it line by line and look like they came from the same artist. Instead, image 12 has drifted into a new style, one picture sits on screen for 15 seconds while three flash by, and 10.00.png imports before 2.00.png. This skill fixes the timing, the style, and the file order before you open your editor.
What it does
- Parses SRT, VTT, or timestamped text and re-cuts it into beats of about 3-5 seconds, so no image lingers or flickers
- Locks one style block and one recurring-character spec, word for word, across every prompt so the look doesn't drift
- Turns abstract lines ("you have no idea why") into concrete visuals and flags lines that have no honest visual
- Runs a 3-image style test, then generates in chunks through your connected image tool, or hands you the prompts and a download script if no tool is connected
- Names files
001_00-04-000.pngso they sort correctly in every OS and editor, and writes a manifest of start and hold times - Checks the finished pack: missing beats, duplicates, timing gaps, and images that went off-style
What you get
A beat sheet with a style-locked prompt for every image, a timestamp-named image folder or the script to build it, a manifest.csv with hold durations, and a coverage report you can trust before editing.
Best for
Faceless YouTube and Shorts creators, sleep and meditation channels, kids-story narrators, and explainer channels who need 20-200 consistent visuals per video without a designer.
SKILL.md preview
---
name: timestamped-voiceover-image-pack
… (sign up to view the full skill)More creator skills
View all Creator skills →Explainer B-Roll Prompt Pack for AI Video
Turns a VO transcript into a style-locked AI video prompt pack: coverage map, P1-P3 clips timed to the VO, exact data routed to code.
Seedance Scene Prompts: Action, Dialogue and Blockouts
Seedance prompts for scenes with people: weighty action, living performances, timed dialogue, multi-clip continuity, and blockout v2v.
Faceless 3D Animated Shorts Pipeline
Concept, timed narration, style bible, and per-scene image, motion, VO, and SFX prompts for faceless 3D shorts that stay consistent.
Seedance 2.0 Video Prompt Writer
Turns an idea into a timecoded multi-shot Seedance 2.0 prompt with camera moves, continuity, reference roles, and synced sound cues.