AIsaAIsaStudio 中文 Open AIsa Studio

NeonClipping open-sources a local engine that turns links into captioned 9:16 clips in about 2 minutes

Original title: 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 released the open-source local clipping engine NeonClipping on GitHub, which turns YouTube/Twitch/Kick videos or local MP4 files into captioned 1080x1920 vertical clips in about two minutes, fully running on the user's machine with no account or upload needed. Fast mode downloads audio only and reads YouTube word-timed captions as transcript (falling back to a local Whisper), scores loudness jumps and 2-4 kHz raised-voice energy, then lets a local LLM via Ollama score moments and write titles and hooks, and downloads only the chosen sections to render clips. Deep mode adds optical-flow motion and cut density. On an RTX 2060, an 85-minute YouTube stream took 97 seconds and a 3-hour Twitch VOD took 136 seconds in Fast mode; ratings from 5-star feedback refit signal weights loca…

Why it matters

An open-source local clipping engine that picks highlights from audio signals plus a local LLM, offering a reusable approach for clip creators who prefer not to upload footage.

Read the original ↗

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Original article

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

The original belongs to GitHub 爆发仓库 and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.