一键在 Manus 中运行任何 Skill

render-cosmic-mythology-voiceover

星标1,046

分支193

更新时间2026年7月19日 03:10

Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cut_dur = VO_dur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x, center crop, zoompan, fade-in first and fade-out last), ffmpeg-concatenated, the VO composited under the picture (libx264 crf18 plus aac), the ONE on-screen hook line faded on over the open with a drawtext alpha window, and Whisper/VEED captions burned along the bottom — never in-world text on a still. This is the FREE deterministic assembly stage (weighted sequence plus Ken-Burns plus concat plus VO composite plus hook overlay plus caption burn); the VO and the stills come from create-vo-elevenlabs and create-image-fal. Use for the cosmic-mythology-voiceover format.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

gooseworks-ai

gooseworks-ai/goose-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

render-cosmic-mythology-voiceover

Assemble a cosmic-mythology-voiceover reel from a config: a faceless, cinematic storytelling video where a warm, contemplative spoken voiceover carries the whole narrative (a "myth as teacher" reframe) over a slow, weighted Ken-Burns zoom across curated cosmic / mythology stills in ONE ethereal deep-indigo + gold look, with ONE on-screen hook line and burned captions. This capability is the FREE, deterministic assembly — the weighted beat-sync sequencing, the Ken-Burns render, the concat, the VO composite, the hook overlay, and the caption burn.

scripts/config.example.json is the worked example (WishAstro "Saturn isn't your villain", ~31s 1080×1920 9:16, 12 weighted Ken-Burns cuts); scripts/PIPELINE.md maps every config block to its source step and scripts/README.md documents the free assembly.

Run

There is a single runnable script — scripts/render.py (config-driven, ffmpeg + Pillow only, NO API keys and NO drawtext/libass required):

python3 scripts/render.py --config config.json --vo working/vo2/vo_atempo.mp3 \
  --stills-dir working/stills --out working/final.mp4 \
  [--words working/vo2/words.json] [--endcard working/endcard.png]

This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are separate capabilities — the spoken VO (create-vo-elevenlabs, ElevenLabs eleven_v3 from a tone-tagged script, atempo time-stretched so the delivered duration sets the timeline) and the 4–6 hero stills in one look pack (create-image-fal, Flux Pro 1.1, reused as repeats to reach the ~10–12 cuts). Given the VO + the stills + the per-cut weight array + the hook line, render.py distributes the cuts across the VO duration by the weighted formula, Ken-Burns-renders each still, concats, composites the VO, fades the hook line on over the open, burns the captions, and (if --endcard is passed) appends a brand end card → the master + a poster. Re-cuts reuse the existing VO / stills and cost $0. See scripts/README.md §0 for the full arg contract.

Contract (the free assembly)

The spoken VO carries the narrative — no talking head, no sung song. The generated/supplied VO IS the audio bed (no music bed by default); do not add a presenter or a second bed.
Plan the timeline AROUND the delivered VO duration. The VO is atempo time-stretched (clamp the factor ≤ ~1.25 so the voice never chipmunks); its delivered length sets the timeline — never trim the VO to a pre-planned grid.
Weighted beat-sync, not a fixed grid. For each cut, cut_dur = VO_dur × weight / Σweights — heavier weights hold longer on the emotional beats (the open, the reframe, the close); the setup cuts run shorter. Every cut stays proportional to the whole VO.
Ken-Burns per still. Render each still with scale 2×, center crop, and a zoompan to the configured zoom_end (~1.10); apply zoom_out on the flagged cuts; fade_in on the FIRST cut and fade_out on the LAST. Stills are reusable — the sequence repeats a few across the cuts.
ONE cosmic look, no in-world text. Every still reads in the single deep-indigo + gold + volumetric-light look; the reel's only text is the hook + the captions, added in post (the "no text, no words" descriptor keeps words off the stills).
ONE hook line, alpha-faded on over the open. Burn the single reframe line over the OPEN only (fade in ~0.5s, hold, fade out ~0.6s) — never a persistent caption, never in-world. render.py does this with a PIL PNG + ffmpeg fade=…:alpha=1 (no drawtext dependency, since stock ffmpeg often lacks it); an ffmpeg drawtext alpha window is an equivalent alternative where available.
Captions from Whisper — bottom, white. VEED/Whisper subtitle burn tracks the spoken VO in the bottom third, white #FFFFFF. If the host ffmpeg lacks libass (no subtitles/ass filter), render the cues as timed PIL PNG overlays (ffmpeg overlay=…:enable='between(t,st,en)') at the same bottom placement — a free local Whisper + ffmpeg burn is the fallback to the VEED tier.
FFmpeg composite, deterministic, FREE. ffmpeg-concat the Ken-Burns clips, composite the VO under the picture (libx264 crf 18 + aac 192k), burn the hook alpha-fade + the caption track → a 1080×1920 h264+aac master (~31s). No paid calls, no keys (the local caption fallback is free).

同仓库更多 Skills

同仓库

create-image-gpt-image-fal

gooseworks-ai/goose-skills

Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's `gpt_image_2`) and gpt-image-2 (`openai/gpt-image-2`, custom output sizes up to 3840px). Routes to text-to-image or the edit variant depending on whether a reference image is provided. Use for photoreal character anchors, scene keyframes, and designed sheets (e.g. storyboards) where precise layout and legible text matter.

2026-07-191.0k

render-cartoon-music-video

gooseworks-ai/goose-skills

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.

2026-07-191.0k

render-creator-pip-listicle

gooseworks-ai/goose-skills

Assemble a creator picture-in-picture product-listicle ad from a config — the creator stays FULL-FRAME the whole beat (voice plus lips generated together per beat, no separate VO, no cut to a full-frame product shot), and on each product beat three persistent overlays ride on top for the WHOLE beat — a title pill top-center, the DEMO in a rounded PiP window top-right (the brand's real UGC clip MUTED, or for a no-UGC brand the product's own autocropped UI still / screen-recording sized to fill the window), and a bottom product card (rounded thumbnail plus 'N · CATEGORY' small-caps plus product NAME in a serif face). Hook plus CTA beats are the creator full-frame with the title pill only. Assembly builds ONE full-1080x1920 transparent overlay PNG per beat, overlays it on the creator clip (cover-scaled to 1080x1920) for the whole beat keeping the native audio, concats all beats, then burns captions LAST as timed PIL PNG overlays (this ffmpeg has no libass) timed deterministically from the known per-beat script.

2026-07-191.0k

render-food-product-sizzle

gooseworks-ai/goose-skills

Assemble a wordless macro-tabletop food-product sizzle ad from a config — normalize fps and SAR across ~4 photorealistic macro clips (hands tearing, flat lay, bite, box hero), concat them, apply a global anti-AI grain pass (eq plus hqdn3d plus noise), composite the audio (a non-diegetic acoustic music bed plus a couple of short diegetic SFX like a snap and a tear placed at measured cue points, loudnorm), composite a STATIC end card entirely in PIL (real logo PNG plus real product PNG plus a serif heritage headline plus a CTA — never AI-rendered text), and burn optional serif stat-callout pills at beats. This is the FREE deterministic assembly stage (normalized concat plus grain plus music and SFX mix plus PIL end card plus callouts); the macro keyframes, i2v clips, and music bed come from create-image-fal, create-video-fal, and create-music-elevenlabs. Use for the food-product-sizzle format.

2026-07-191.0k

render-split-screen-creator

gooseworks-ai/goose-skills

Assemble a split-screen creator ad from a config — a two-zone vertical composite where a supplied AI-creator lip-sync take fills the BOTTOM ~48% while real 16:9 product/demo clips run uncropped in the TOP ~52%, each top clip contain-fit with a darkened blurred cover-scale fill of the same clip (never black bars), a 3px brand-color divider between the zones, the creator slice cover-fit per the per-scene VO timing, scenes hard-concatenated with the body audio being the concatenated creator VO slices, an end card held on the last sharp frame ~3s, then the ASSEMBLED cut transcribed with local Whisper (not the raw VO — concat drops inter-scene silence) and word-level captions burned in the chosen style. This is the FREE deterministic assembly + caption stage (two-zone composite + blurred fill + divider + hard-concat + end card + captions); the VO comes from create-vo-elevenlabs, the anchor from create-image-gpt-image-fal, and the whole-VO lip-sync from a paid VEED Fabric 1.0 take (a no-atom upstream input). Use fo

2026-07-191.0k

create-video-seedance-2-fal

gooseworks-ai/goose-skills

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.

2026-07-191.0k

name	render-cosmic-mythology-voiceover
description	Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cut_dur = VO_dur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x, center crop, zoompan, fade-in first and fade-out last), ffmpeg-concatenated, the VO composited under the picture (libx264 crf18 plus aac), the ONE on-screen hook line faded on over the open with a drawtext alpha window, and Whisper/VEED captions burned along the bottom — never in-world text on a still. This is the FREE deterministic assembly stage (weighted sequence plus Ken-Burns plus concat plus VO composite plus hook overlay plus caption burn); the VO and the stills come from create-vo-elevenlabs and create-image-fal. Use for the cosmic-mythology-voiceover format.
status	active

render-cosmic-mythology-voiceover

Run

There is a single runnable script — scripts/render.py (config-driven, ffmpeg + Pillow only, NO API keys and NO drawtext/libass required):

python3 scripts/render.py --config config.json --vo working/vo2/vo_atempo.mp3 \
  --stills-dir working/stills --out working/final.mp4 \
  [--words working/vo2/words.json] [--endcard working/endcard.png]

Contract (the free assembly)

The spoken VO carries the narrative — no talking head, no sung song. The generated/supplied VO IS the audio bed (no music bed by default); do not add a presenter or a second bed.
Plan the timeline AROUND the delivered VO duration. The VO is atempo time-stretched (clamp the factor ≤ ~1.25 so the voice never chipmunks); its delivered length sets the timeline — never trim the VO to a pre-planned grid.
Weighted beat-sync, not a fixed grid. For each cut, cut_dur = VO_dur × weight / Σweights — heavier weights hold longer on the emotional beats (the open, the reframe, the close); the setup cuts run shorter. Every cut stays proportional to the whole VO.
Ken-Burns per still. Render each still with scale 2×, center crop, and a zoompan to the configured zoom_end (~1.10); apply zoom_out on the flagged cuts; fade_in on the FIRST cut and fade_out on the LAST. Stills are reusable — the sequence repeats a few across the cuts.
ONE cosmic look, no in-world text. Every still reads in the single deep-indigo + gold + volumetric-light look; the reel's only text is the hook + the captions, added in post (the "no text, no words" descriptor keeps words off the stills).
ONE hook line, alpha-faded on over the open. Burn the single reframe line over the OPEN only (fade in ~0.5s, hold, fade out ~0.6s) — never a persistent caption, never in-world. render.py does this with a PIL PNG + ffmpeg fade=…:alpha=1 (no drawtext dependency, since stock ffmpeg often lacks it); an ffmpeg drawtext alpha window is an equivalent alternative where available.
Captions from Whisper — bottom, white. VEED/Whisper subtitle burn tracks the spoken VO in the bottom third, white #FFFFFF. If the host ffmpeg lacks libass (no subtitles/ass filter), render the cues as timed PIL PNG overlays (ffmpeg overlay=…:enable='between(t,st,en)') at the same bottom placement — a free local Whisper + ffmpeg burn is the fallback to the VEED tier.
FFmpeg composite, deterministic, FREE. ffmpeg-concat the Ken-Burns clips, composite the VO under the picture (libx264 crf 18 + aac 192k), burn the hook alpha-fade + the caption track → a 1080×1920 h264+aac master (~31s). No paid calls, no keys (the local caption fallback is free).