ClipLedger — Source-Linked Shorts

by:Román Romero

Turn your own video and matching SRT into source-linked vertical clips: MP4s, editable subtitles, a review page and original time ranges. Render locally with Python and FFmpeg, without a paid video API or per-render service fee. No transcription, URL download or publishing. Review context, caption alignment and audio before posting.

notebooklm

by:cheahhl814

Programmatic access to Google NotebookLM via the nlm CLI — manages notebooks, sources, queries, and artifacts with citation-quality source titles.

VideoDB - 免费Claude Skill

by:Irene561

VideoDB 来自 affaan-m 的 ECC 项目，可用于导入、理解、搜索、编辑和监控来自本地文件、URL、直播流或桌面会话的视频与音频。它可以建立视觉和语音索引，按时间戳定位关键片段，生成剪辑和字幕，转码媒体，添加文字、图片或音频叠加，并为直播中的特定事件创建实时提醒。基于 VideoDB SDK 和 API 运行。

LLM Context Modular Docs

by:Ahmed Rehan

Structure project docs as modular memory + reasoning files so AI agents load only what they need — cutting token usage by 70–96% per query. Grounded in Anthropic, LangChain, and Crawl4AI's production llm.txt research. Implements write/select/compress/isolate context engineering strategies.

30-Min Video → 5 Shorts Picks with ffmpeg Cuts

by:minwoo1999

Stop rewatching long videos to find clips. Drop in a YouTube URL and get Shorts candidate cards with timecodes, a first-3-seconds hook, a vertical script, and paste-ready ffmpeg cut commands. Transcripts come via yt-dlp (manual subtitles first, auto fallback); picks are ranked against a 9-type hook catalog and a 5-point checklist. Conditions like "under 45s only" apply as-is; exclusions are reported with reasons. Includes 2 Python scripts (343 lines). No video editing or speech-to-text.

Voice Studio — 대본 한 장이 방송급 음성·유튜브 영상이 됩니다

by:minwoo1999

마이크도, 녹음실도, 편집 툴도 없이 대본 한 장으로 유튜브에 바로 올릴 영상을 만듭니다. 4개 신경망 TTS 엔진(edge·Kokoro·OpenAI·ElevenLabs) 중 골라 나레이션을 합성하고, BGM을 자동 덕킹으로 깔고, 유튜브 표준 -14 LUFS로 마스터링한 뒤, 커버/웨이브폼 비주얼과 자막(SRT)까지 얹은 mp4로 패키징 — 명령 4줄이면 끝납니다. 2인 팟캐스트 대화 합성, 쇼츠 세로 영상, 로컬 Whisper 전사(회의록·자막)까지 지원. 기본 엔진은 무료·API 키 불필요, 설치는 uv가 전부 자동. TTS 엔진별 상업 이용 라이선스 가이드와 2026 유튜브 AI 콘텐츠 정책 가이드를 정직하게 동봉했습니다.

LongCut AI

by:kunku kim

Turn one long speech-led video into a tighter finished MP4 at your target length — without cutting away the context that makes it make sense.

MemoryInterface｜LLMエージェント永続メモリ層

by:Assistant Gomez

LLMエージェントがセッションをまたいで記憶を保持するための永続メモリ層。抽象基底クラス MemoryStore ＋ LocalJSONStore 実装で、保存・取得・検索を再利用可能に。Karpathy の「LLM OS（記憶＝ディスク層）」着想。バックエンド差し替え可・Python標準ライブラリのみ・LLM呼び出しゼロ・ユニットテスト同梱。