render-cosmic-mythology-voiceover

Name: render-cosmic-mythology-voiceover
Author: gooseworks-ai

1.0kstars193forks

How to install render-cosmic-mythology-voiceover?

gooseworks-ai/goose-skills/render-cosmic-mythology-voiceover

$npx -y skills add gooseworks-ai/goose-skills --skill render-cosmic-mythology-voiceover

Installs into the current project.

Summary

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 longe

Files · 1

View on GitHub

SKILL.md

1	# render-cosmic-mythology-voiceover
2
3	Assemble a cosmic-mythology-voiceover reel from a config: a faceless, cinematic storytelling
4	video where a warm, contemplative spoken voiceover carries the whole narrative (a "myth as
5	teacher" reframe) over a slow, weighted Ken-Burns zoom across curated cosmic / mythology stills
6	in ONE ethereal deep-indigo + gold look, with ONE on-screen hook line and burned captions. This
7	capability is the FREE, deterministic assembly — the weighted beat-sync sequencing, the
8	Ken-Burns render, the concat, the VO composite, the hook overlay, and the caption burn.
9
10	`scripts/config.example.json` is the worked example (WishAstro "Saturn isn't your villain", ~31s
11	1080×1920 9:16, 12 weighted Ken-Burns cuts); `scripts/PIPELINE.md` maps every config block to its
12	source step and `scripts/README.md` documents the free assembly.
13
14	## Run
15
16	There is a single runnable script — `scripts/render.py` (config-driven, ffmpeg + Pillow only, NO
17	API keys and NO `drawtext`/`libass` required):
18
19	```bash
20	python3 scripts/render.py --config config.json --vo working/vo2/vo_atempo.mp3 \
21	--stills-dir working/stills --out working/final.mp4 \
22	[--words working/vo2/words.json] [--endcard working/endcard.png]
23	```
24
25	This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
26	separate capabilities — the spoken VO (`create-vo-elevenlabs`, ElevenLabs `eleven_v3` from a
27	tone-tagged script, atempo time-stretched so the delivered duration sets the timeline) and the 4–6
28	hero stills in one look pack (`create-image-fal`, Flux Pro 1.1, reused as repeats to reach the
29	~10–12 cuts). Given the VO + the stills + the per-cut weight array + the hook line, `render.py`
30	distributes the cuts across the VO duration by the weighted formula, Ken-Burns-renders each still,
31	concats, composites the VO, fades the hook line on over the open, burns the captions, and (if
32	`--endcard` is passed) appends a brand end card → the master + a poster. Re-cuts reuse the existing
33	VO / stills and cost $0. See `scripts/README.md` §0 for the full arg contract.
34
35	## Contract (the free assembly)
36
37	- The spoken VO carries the narrative — no talking head, no sung song. The generated/supplied
38	VO IS the audio bed (no music bed by default); do not add a presenter or a second bed.
39	- Plan the timeline AROUND the delivered VO duration. The VO is atempo time-stretched (clamp
40	the factor ≤ ~1.25 so the voice never chipmunks); its delivered length sets the timeline — never
41	trim the VO to a pre-planned grid.
42	- Weighted beat-sync, not a fixed grid. For each cut, `cut_dur = VO_dur × weight / Σweights` —
43	heavier weights hold longer on the emotional beats (the open, the reframe, the close); the setup
44	cuts run shorter. Every cut stays proportional to the whole VO.
45	- Ken-Burns per still. Render each still with scale 2×, center crop, and a `zoompan` to the
46	configured `zoom_end` (~1.10); apply `zoom_out` on the flagged cuts; `fade_in` on the FIRST cut
47	and `fade_out` on the LAST. Stills are reusable — the sequence repeats a few across the cuts.
48	- ONE cosmic look, no in-world text. Every still reads in the single deep-indigo + gold +
49	volumetric-light look; the reel's only text is the hook + the captions, added in post (the "no
50	text, no words" descriptor keeps words off the stills).
51	- ONE hook line, alpha-faded on over the open. Burn the single reframe line over the OPEN only
52	(fade in ~0.5s, hold, fade out ~0.6s) — never a persistent caption, never in-world. `render.py`
53	does this with a PIL PNG + ffmpeg `fade=…:alpha=1` (no `drawtext` dependency, since stock ffmpeg
54	often lacks it); an ffmpeg `drawtext` alpha window is an equivalent alternative where available.
55	- Captions from Whisper — bottom, white. VEED/Whisper subtitle burn tracks the spoken VO in the
56	bottom third, white `#FFFFFF`. If the host ffmpeg lacks libass (no `subtitles`/`ass` filter),
57	render the cues as timed PIL PNG overlays (ffmpeg `overlay=…:enable='between(t,st,en)'`) a

People who liked this also viewed

6 picks

Type

render-cosmic-mythology-voiceover

1.0kstars193forks

View on GitHub

How to install render-cosmic-mythology-voiceover?

gooseworks-ai/goose-skills/render-cosmic-mythology-voiceover

$npx -y skills add gooseworks-ai/goose-skills --skill render-cosmic-mythology-voiceover

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# render-cosmic-mythology-voiceover
2
3	Assemble a cosmic-mythology-voiceover reel from a config: a faceless, cinematic storytelling
4	video where a warm, contemplative spoken voiceover carries the whole narrative (a "myth as
5	teacher" reframe) over a slow, weighted Ken-Burns zoom across curated cosmic / mythology stills
6	in ONE ethereal deep-indigo + gold look, with ONE on-screen hook line and burned captions. This
7	capability is the FREE, deterministic assembly — the weighted beat-sync sequencing, the
8	Ken-Burns render, the concat, the VO composite, the hook overlay, and the caption burn.
9
10	`scripts/config.example.json` is the worked example (WishAstro "Saturn isn't your villain", ~31s
11	1080×1920 9:16, 12 weighted Ken-Burns cuts); `scripts/PIPELINE.md` maps every config block to its
12	source step and `scripts/README.md` documents the free assembly.
13
14	## Run
15
16	There is a single runnable script — `scripts/render.py` (config-driven, ffmpeg + Pillow only, NO
17	API keys and NO `drawtext`/`libass` required):
18
19	```bash
20	python3 scripts/render.py --config config.json --vo working/vo2/vo_atempo.mp3 \
21	--stills-dir working/stills --out working/final.mp4 \
22	[--words working/vo2/words.json] [--endcard working/endcard.png]
23	```
24
25	This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
26	separate capabilities — the spoken VO (`create-vo-elevenlabs`, ElevenLabs `eleven_v3` from a
27	tone-tagged script, atempo time-stretched so the delivered duration sets the timeline) and the 4–6
28	hero stills in one look pack (`create-image-fal`, Flux Pro 1.1, reused as repeats to reach the
29	~10–12 cuts). Given the VO + the stills + the per-cut weight array + the hook line, `render.py`
30	distributes the cuts across the VO duration by the weighted formula, Ken-Burns-renders each still,
31	concats, composites the VO, fades the hook line on over the open, burns the captions, and (if
32	`--endcard` is passed) appends a brand end card → the master + a poster. Re-cuts reuse the existing
33	VO / stills and cost $0. See `scripts/README.md` §0 for the full arg contract.
34
35	## Contract (the free assembly)
36
37	- The spoken VO carries the narrative — no talking head, no sung song. The generated/supplied
38	VO IS the audio bed (no music bed by default); do not add a presenter or a second bed.
39	- Plan the timeline AROUND the delivered VO duration. The VO is atempo time-stretched (clamp
40	the factor ≤ ~1.25 so the voice never chipmunks); its delivered length sets the timeline — never
41	trim the VO to a pre-planned grid.
42	- Weighted beat-sync, not a fixed grid. For each cut, `cut_dur = VO_dur × weight / Σweights` —
43	heavier weights hold longer on the emotional beats (the open, the reframe, the close); the setup
44	cuts run shorter. Every cut stays proportional to the whole VO.
45	- Ken-Burns per still. Render each still with scale 2×, center crop, and a `zoompan` to the
46	configured `zoom_end` (~1.10); apply `zoom_out` on the flagged cuts; `fade_in` on the FIRST cut
47	and `fade_out` on the LAST. Stills are reusable — the sequence repeats a few across the cuts.
48	- ONE cosmic look, no in-world text. Every still reads in the single deep-indigo + gold +
49	volumetric-light look; the reel's only text is the hook + the captions, added in post (the "no
50	text, no words" descriptor keeps words off the stills).
51	- ONE hook line, alpha-faded on over the open. Burn the single reframe line over the OPEN only
52	(fade in ~0.5s, hold, fade out ~0.6s) — never a persistent caption, never in-world. `render.py`
53	does this with a PIL PNG + ffmpeg `fade=…:alpha=1` (no `drawtext` dependency, since stock ffmpeg
54	often lacks it); an ffmpeg `drawtext` alpha window is an equivalent alternative where available.
55	- Captions from Whisper — bottom, white. VEED/Whisper subtitle burn tracks the spoken VO in the
56	bottom third, white `#FFFFFF`. If the host ffmpeg lacks libass (no `subtitles`/`ass` filter),
57	render the cues as timed PIL PNG overlays (ffmpeg `overlay=…:enable='between(t,st,en)'`) a

People who liked this also viewed

6 picks

Type