AIsaAIsaStudio English 打开 AIsa Studio

NeonClipping 开源:贴链接两分钟生成带字幕 9:16 切片的本地剪辑引擎

原标题:iamajmeena/neonclipping: Paste a link, get captioned 9:16 clips in ~2 min. Free, local, open-source clipping engine (audio-first, YouTube captions, local LLM).

Ajay K Meena 在 GitHub 开源本地剪辑引擎 NeonClipping,可将 YouTube/Twitch/Kick 视频或本地 MP4 转成带字幕的 1080x1920 竖版切片,全程在本地运行,无需账号或上传。Fast 模式只下载音频,用 YouTube 词级字幕作转写(其他来源回退到本地 Whisper),按响度跳变和 2-4 kHz 高声能量等信号打分,再由 Ollama 本地 LLM 评分并生成标题和 hook,只下载选中片段渲染成片。Deep 模式额外加入光流运动和镜头切换密度。实测 RTX 2060 上,85 分钟 YouTube 直播录像 Fast 模式 97 秒、3 小时 Twitch VOD 136 秒;用户 5 星评分在本地以岭回归微调信号权重,8 条评分后生效。

为什么值得看

本地开源剪辑工具,音频信号加本地 LLM 挑选高光,全流程不联网,对剪切片创作者有可借鉴的思路。

阅读原文 ↗

本页的摘要、推荐理由与解读出自 AIsa Studio 的 AI 风向智能体,原文版权归原作者所有。

原文

GitHub 上的新仓库 iamajmeena/neonclipping,创建 1 天,已有 1062 星(平均每天 850 星)。 Paste a link, get captioned 9:16 clips in ~2 min. Free, local, open-source clipping engine (audio-first, YouTube captions, local LLM). 主题:clipping, ffmpeg, shorts, video, whisper, yt-dlp 语言:Python

README:

NeonClipping

Paste a link. Get captioned 9:16 clips in about two minutes. Free, local, open-source.

NeonClipping turns long YouTube / Twitch / Kick videos (or your own MP4) into vertical, captioned clips with a title and hook for each. Everything runs on your machine: no account, no subscription, no upload.

Star on GitHub Instagram

🌐 Website with one-click Windows setup:

Made by Ajay K Meena (Director, DOP, colorist, DaVinci Resolve educator, Jaipur). If NeonClipping saves you time, please ⭐ star the repo and follow @iamajmeena on Instagram.

demo

UI

📘 Guides (Hindi + English, PDF): docs/NeonClipping-Guide-EN-HI.pdf
🤖 Let an AI agent install it for you: copy docs/NEONCLIPPING-AGENT-SETUP-PROMPT.txt into Claude Code, Codex CLI or Cursor.

How it finds good moments

Two modes, one button.

⚡ Fast mode (default, videos over 10 min) copies the trick that makes the fastest clippers fast: never look at the whole video.

  1. Download audio only (79 MB for an 85-minute video, about 10 s).
  2. Take the transcript for free from YouTube's own captions (word-timed). No speech model needed. For other sources a local Whisper model is used as the fallback.
  3. Score the whole audio track for sudden loudness jumps (vs a 2-minute local baseline), raised voices (2–4 kHz energy) and quiet-to-loud transitions.
  4. Take the best moments, read each one's transcript with a local LLM (Ollama) and let it score the moment, write a title and a hook. Snap the start and end to sentence boundaries inside your Min/Max length.
  5. Download only the chosen sections of the video (not the whole file), trim exactly by matching their sound to the audio track, and render 1080x1920 clips with burned-in captions.

🔬 Deep mode downloads the whole video, adds optical-flow motion (OpenCV Farneback: fast objects, impacts, camera whips) and cut density to the audio signals, shortlists 4× more candidates and gives the LLM 15 seconds of context before and after each one.

Measured on one machine (RTX 2060, 16 threads), Fast mode, 3 clips each:

Source Time
85-minute YouTube stream (YouTube captions) 97 s
3-hour Twitch VOD (no captions, local speech model) 136 s
90-second YouTube trailer 21 s
90-second local MP4 14 s

Your numbers depend on network and CPU.

How it decides what is a good moment

Every candidate moment is scored from several signals, then the best ones are kept:

Signal What it looks for
Loudness jump A sudden boom or shout compared with the last two minutes
Raised voice Energy in the 2–4 kHz band (screaming, yelling)
What is said "oh my god", "oh shit", "run", "police", "bhaago", "arre yaar" and similar (English, Hinglish, Hindi)
On-screen action Fast motion (optical flow), explosion-like flashes, red/blue light flicker, scene cuts
AI score A small local LLM reads the transcript: emotion, punchline, payoff

It learns from you. Under every clip there are 5 stars. Your ratings stay on your computer (data/feedback.jsonl). After 8 ratings the weights of the signals above are re-fitted (ridge regression pulled toward the defaults, blended in gradually), so a gamer-shouting-heavy taste ranks shouting higher and a calm-explainer taste ranks it lower. Nothing is uploaded.

Features

  • One-click Make clips, live progress, clips appear one by one with preview and MP4 download.
  • Min / Max clip length (e.g. 30–80 s). Clips end on a sentence.
  • Facecam position presets (top-left, top-right, bottom-left, bottom-right, bottom-centre, none) for the usual streamer layouts, remembered between sessions. Or draw the face and gameplay boxes yourself in the editor.
  • 11 native layouts: camera above/below gameplay, blurred fill, full-screen crop, gameplay only, four corner overlays, circle facecam and side-by-side. Independent face/game selection and a face-size slider. Preview-only platform safe zones.
  • Caption styles: GTA Neon, Impact, Clean, Hormozi and MrBeast. Word-timed, editable words, SRT export.
  • Opening headings: eight seconds by default, adjustable from 2–60 seconds, with black backing for bright gameplay and facecam layouts. Use Improve opening heading to write a grounded curiosity question from the selected transcript. Existing clips can apply the new look without downloading or finding moments again.
  • Moment mix: Balanced combines activity and transcript-led proposals; Action favours energy; Dialogue favours story, humour and insights. Final selection reduces overlapping and repetitive moments. Balanced/Dialogue prefer an already-installed Gemma 4 local judge; other local models remain a fallback. This changes curation rules and prompts, not foundation-model weights.
  • Custom captions: installed font family, size, text/active/outline colours, words per caption and local saved profiles. Import SRT/ASS/WebVTT or paste subtitle text, adjust word timings, split/merge and shift captions. Within-cue word timings from imported files are estimated. Download WebVTT alongside SRT.
  • Transcript explorer: explicitly generate or import a full-source transcript, search phrases across cues, browse pages, and click the first/last word to export that passage. Cached transcripts are reused by Make clips and invalidated when the source changes.
  • Hinglish captions: Hindi speech is w

原文版权归 GitHub 爆发仓库 及原作者所有,本站转载仅供阅读。如需删除,请联系 support@aisa.one。