無料GitHub で公開

karaoke-captions

Generate TikTok/Shorts-style karaoke captions using MLX Whisper, ASS subtitles, and FFmpeg libass. Use when burning word-level highlight captions into a video, matching caption style from a screenshot, rendering ASS karaoke subtitles, or when the user runs /karaoke-captions.

AI-Builder-Club/skills

インストール方法を見る

含まれるファイル（11）

SKILL.md3.3 KB
.gitignore269 B
presets/style.json369 B
presets/yellow.json369 B
README.md1.7 KB
references/style-guide.md2.7 KB
requirements.txt25 B
scripts/extract_words.py2.0 KB
scripts/gen_ass.py7.3 KB
scripts/match_style_from_image.py4.2 KB
scripts/render.sh1.3 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Karaoke Captions Skill

Generate dynamic, TikTok/Shorts-style karaoke captions with word-level highlight sweeps using ASS subtitles and FFmpeg libass. Supports style matching from a reference screenshot.

Scripts, presets, and references live next to this skill. Run the commands from the skill directory (or pass absolute paths).

Requirements

macOS with Apple Silicon (MLX Whisper)
Python 3.10+
FFmpeg with libass (brew install ffmpeg)

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

reference.png --------(match_style_from_image.py)--------> style.json --+
                                                                   +--(gen_ass.py)--> captions.ass --(render.sh)--> output.mp4
input.mp4 ---------------------------------->(extract_words.py)--> words.json --+

File Architecture

File	Purpose	Role
`input.mp4`	Source video	Input
`reference.png`	Style reference image (optional)	Visual Prompt
`words.json`	Word-level timestamps `[{"word": ..., "start": ..., "end": ...}]`	Persistent Raw Data
`style.json`	Font, size, highlight color, outline, soft shadow, margin, words per line	Style Config
`captions.ass`	ASS subtitle script with two-layer blurred drop shadow and inline color overrides	Generated Intermediate
`output.mp4`	Final video with burned-in subtitles	Output Deliverable

Standard Workflow

Step 1. Extract Word Timestamps

python scripts/extract_words.py \
  input.mp4 words.json \
  --model mlx-community/whisper-large-v3-turbo

(For Chinese videos, add --language zh).

Step 2. Select Style or Auto-match from Reference Image

From Reference Image:

python scripts/match_style_from_image.py \
  reference.png style.json --video input.mp4

From Presets:
- presets/style.json: Default neon green highlight (#00FF00), Arial Black, all-caps, 4 words/line.
- presets/yellow.json: Yellow highlight (#FFFF00), Arial Black, all-caps.

To adjust appearance manually, see Style Guide.

Step 3. Generate ASS Subtitles

python scripts/gen_ass.py \
  words.json style.json captions.ass --video input.mp4

Step 4. Render Preview & Visual Check

# Preview segment:
scripts/render.sh input.mp4 captions.ass preview.mp4 3 8

# Frame snapshot:
scripts/render.sh frame input.mp4 captions.ass preview_frame.png 4.5

Step 5. Render Final Video

scripts/render.sh input.mp4 captions.ass output.mp4

References & Presets

Style Guide
Presets:
- presets/style.json
- presets/yellow.json
Scripts:

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

agent-context-audit

無料

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.

日本語の概要は準備中です。原文の説明を表示しています。