AI剪口播
Free口播视频转录和口误识别。生成审查稿和删除任务清单。触发词:剪口播、处理视频、识别口误
The English summary is being prepared. Showing the original description.
Render, preview, validate, and burn consistent production subtitles from QC-passed real-timestamp caption artifacts. Use for AI-video production, washed-video production, IndexTTS2 explainers, practical long-form videos, talking-head edits, Kimi-style dark rounded captions, warm-white translucent captions, subtitle styling, subtitle overlays, or fixing caption size, position, shadow, drift, and 4K scaling. Always pair with ra-audio-to-subtitles when final word timestamps do not already exist.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Separate subtitle timing from subtitle appearance:
ra-audio-to-subtitles own ASR, phrase grouping, timestamps, SRT/VTT, and
caption-qc.json.ra-audio-to-subtitles unless the project already has the canonical
caption artifacts described in references/timing-contract.md.caption-qc.json to report status: pass.references/style-registry.json. Use anchor-dark
when the contract does not specify another style.references/layout-qc.md.scripts/validate_caption_render.py and archive its JSON report.anchor-dark reproduces the approved Kimi K3 subtitle treatment: STHeiti
Medium, warm white text, a tight charcoal translucent rounded panel, no text
stroke, no text shadow, no large panel shadow, and a fixed bottom-center
anchor. Read references/style-anchor-dark.md before changing its values.
anchor-light keeps the exact same typography, size, padding, width, bottom
anchor, line fitting, and resolution scaling as anchor-dark. Only its surface
changes: dark ink on a warm-white translucent panel with a fine border and
subtle soft shadow. Read references/style-anchor-light.md before changing its
values. This is the second registered style; anchor-dark remains the default.
Scale every 1080p metric by target_height / 1080. Render 4K captions at 2×
their 1080p measurements; never upscale a rasterized 1080p subtitle layer.
Preview a QC-passed project:
python3 .claude/skills/skill-captions/scripts/render_captions.py \
final.mp4 media/captions/captions.json \
--qc media/captions/caption-qc.json \
--preview qc/caption-preview.png \
--preview-only
Burn the default style:
python3 .claude/skills/skill-captions/scripts/render_captions.py \
final-clean.mp4 media/captions/captions.json \
--qc media/captions/caption-qc.json \
--out renders/final-captioned.mp4 \
--preview qc/caption-preview.png
Burn the light translucent style:
python3 .claude/skills/skill-captions/scripts/render_captions.py \
final-clean.mp4 media/captions/captions.json \
--qc media/captions/caption-qc.json \
--style anchor-light \
--out renders/final-captioned.mp4 \
--preview qc/caption-preview.png
Skip an interval that already contains burned captions:
python3 .claude/skills/skill-captions/scripts/render_captions.py \
final-clean.mp4 media/captions/captions.json \
--qc media/captions/caption-qc.json \
--exclude 0:23.936 \
--out renders/final-captioned.mp4
Create a reusable transparent caption band:
python3 .claude/skills/skill-captions/scripts/render_captions.py \
final-clean.mp4 media/captions/captions.json \
--qc media/captions/caption-qc.json \
--overlay-out renders/caption-band.mov
Validate the result:
python3 .claude/skills/skill-captions/scripts/validate_caption_render.py \
--source final-clean.mp4 \
--render renders/final-captioned.mp4 \
--captions media/captions/captions.json \
--qc media/captions/caption-qc.json \
--out qc/caption-render-qc.json
captions.json start/end values directly.embedded-captions
lane.Video orchestrators should call this skill after ra-audio-to-subtitles.
Handoff contracts may set caption_style to anchor-dark or anchor-light;
otherwise use anchor-dark.
Renderers may reproduce the registered CSS in Remotion or HyperFrames, but
must preserve the style metrics and fixed-anchor behavior.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
口播视频转录和口误识别。生成审查稿和删除任务清单。触发词:剪口播、处理视频、识别口误
The English summary is being prepared. Showing the original description.
将法天象地、同源巨大法相或角色力量显现的视觉参考制作成连续关键帧,再使用用户选择或可用的图生视频工具分段生成、检查和合成动作视频,不绑定成片平台。适用于本体与法相同框、领域展开、凝实与同步出招;不负责整部小说改编或普通图片轮播。
The English summary is being prepared. Showing the original description.
口播基础素材包生成。转录口播、识别口误、生成审核页;用户确认后剪出新视频,Agent 再基于剪后视频重新转写、AI 校对字幕,输出后续口播成片可用的 source_cut.mp4 和 subtitles.srt。触发词:剪口播、处理口播素材、准备口播素材、识别口误、基础素材包
The English summary is being prepared. Showing the original description.
口播视频成片 Skill。把文章/口播稿/SRT、剪后视频和 HTML/图片素材串成分镜稿、时间线预览和最终 MP4;成片比例和动画风格从用户配置读取,动画默认使用小黑风格。触发词:口播成片、做分镜稿、时间线预览、合成口播视频、导出竖屏MP4
The English summary is being prepared. Showing the original description.
自进化 skills。记录用户反馈,更新方法论和规则。触发词:更新规则、记录反馈、改进skill
The English summary is being prepared. Showing the original description.
dontbesilent 商业工具箱主入口。双模式:任务前路由(你的问题该用哪个 skill)+ 任务后导航(刚做完诊断,下一步该干什么)。 触发方式:/dbs、/商业、「帮我看看」、「下一步怎么走」 Main entry point for dontbesilent business toolkit. Dual mode: pre-task routing + post-task navigation. Trigger: /dbs, "help me with my business", "what's next"
The English summary is being prepared. Showing the original description.