Communitygithub.com

Army161/OpenMontage

Verstehen Sie Videoinhalte lokal mithilfe von ffmpeg-Frame-Extraktion und Whisper-Transkription. Keine API-Schlüssel erforderlich.

Was ist OpenMontage?

Diese Fähigkeit ermöglicht es KI-Agenten, Videoinhalte vollständig lokal zu verarbeiten, ohne auf externe APIs angewiesen zu sein. Sie extrahiert Schlüsselbilder (Frames) mit ffmpeg und transkribiert Audiospuren mit OpenAIs Whisper-Modell. Der Agent kann Szenenwechsel erkennen, I-Frames extrahieren oder in regelmäßigen Abständen Bilder sammeln. Die Ausgabe erfolgt als strukturiertes JSON mit Pfaden zu den extrahierten Bildern, Zeitstempeln und dem vollständigen Transkript. Dies ist ideal für Workflows, die Videobeschreibungen, visuelle Analysen oder barrierefreie Transkriptionen benötigen – alles offline und ohne datenschutzrechtliche Bedenken. Unterstützt wird die Ausführung über Befehlszeilenparameter, die die Extraktionsmethode, die Anzahl der Frames und die Größe des Whisper-Modells steuern.

Funktioniert mit~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/Army161/OpenMontage/tree/HEAD/.agents/skills/video-understand

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

video-verstehen

Verstehen Sie Videoinhalte lokal mithilfe von ffmpeg für die Frame-Extraktion und Whisper für die Transkription. Vollständig offline, keine API-Schlüssel erforderlich.

Voraussetzungen

  • ffmpeg + ffprobe (erforderlich): brew install ffmpeg
  • openai-whisper (optional, für Transkription): pip install openai-whisper

Befehle

# Szenenerkennung + Transkription (Standard)
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4

# Extraktion von Schlüsselbildern
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4 -m keyframe

# Extraktion in regelmäßigen Abständen
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4 -m interval

# Begrenzung der extrahierten Bilder
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4 --max-frames 10

# Verwendung eines größeren Whisper-Modells
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4 --whisper-model small

# Nur Bilder, keine Transkription
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4 --no-transcribe

# Stillen Modus (nur JSON, keine Fortschrittsanzeige)
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4 -q

# Ausgabe in Datei
python3 skills/video-verstehen/scripts/video_verstehen.py video.mp4 -o ergebnis.json

CLI-Optionen

FlagBeschreibung
videoEingabevideodatei (positionsabhängig, erforderlich)
-m, --modeExtraktionsmodus: scene (Standard), keyframe, interval
--max-framesMaximale Anzahl zu behaltender Bilder (Standard: 20)
--whisper-modelGröße des Whisper-Modells: tiny, base, small, medium, large (Standard: base)
--no-transcribeÜberspringt die Audiotranskription, extrahiert nur Bilder
-o, --outputSchreibt Ergebnis-JSON in eine Datei anstatt auf stdout
-q, --quietUnterdrückt Fortschrittsmeldungen, gibt nur JSON aus

Extraktionsmodi

ModusFunktionsweiseAm besten geeignet für
sceneErkennt Szenenwechsel mittels ffmpeg select='gt(scene,0.3)'Die meisten Videos, abwechslungsreiche Inhalte
keyframeExtrahiert I-Frames (Codec-Schlüsselbilder)Codierte Videos mit natürlicher Schlüsselbildplatzierung
intervalGleichmäßig verteilte Bilder basierend auf Dauer und max-framesFeste Abtastung, vorhersehbare Ausgabe

Wenn der Modus scene keine Szenenwechsel erkennt, fällt er automatisch auf den Modus interval zurück.

Ausgabe

Das Skript gibt JSON auf stdout aus (oder in eine Datei mit -o). Siehe references/ausgabe-format.md für das vollständige Schema.

{
  "video": "video.mp4",
  "duration": 18.076,
  "resolution": {"width": 1224, "height": 1080},
  "mode": "scene",
  "frames": [
    {"path": "/abs/path/frame_0001.jpg", "timestamp": 0.0, "timestamp_formatted": "00:00"}
  ],
  "frame_count": 12,
  "transcript": [
    {"start": 0.0, "end": 2.5, "text": "Hallo und willkommen..."}
  ],
  "text": "Gesamtes Transkript...",
  "note": "Verwenden Sie das Lesen-Werkzeug, um Frame-Bilder zur visuellen Analyse anzuzeigen."
}

Verwenden Sie das Lesen-Werkzeug auf den Pfaden der Frame-Bilder, um extrahierte Bilder visuell zu inspizieren.

Referenzen

  • references/ausgabe-format.md -- Vollständige Dokumentation des JSON-Ausgabeformats

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

Army161/OpenMontage

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax). Supports two gateways: HeyGen API and fal.ai API.

Army161/OpenMontage

Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API. Use when: (1) Choosing a specific avatar and voice for a video, (2) Writing exact scripts for an avatar to speak, (3) Building multi-scene videos with different backgrounds per scene, (4) Creating transparent WebM videos for compositing, (5) Using talking photos as video presenters, (6) Integrating HeyGen avatars with Remotion, (7) Batch video generation with exact specs, (8) Brand-consistent production videos with precise control.

Army161/OpenMontage

Use p5.js/canvas for local procedural character effects: particles, weather, squash/stretch, walk cycles, and environmental motion.

Army161/OpenMontage

Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.

Army161/OpenMontage

Create videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) One-shot prompt-to-video generation, (6) User says "make me a video" or "create a video about X".

Army161/OpenMontage

Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Use when creating Chinese voiceovers, when the user prefers Doubao/Volcengine/火山引擎/豆包 TTS, or when narration needs character-level timestamp metadata for subtitles.

Army161/OpenMontage

Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.

Army161/OpenMontage

Use when implementing Disney's 12 animation principles with Framer Motion in React applications

Army161/OpenMontage

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.

Army161/OpenMontage

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

Army161/OpenMontage

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

Army161/OpenMontage

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

Army161/OpenMontage

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

Army161/OpenMontage

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

Army161/OpenMontage

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (website-to-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.

Army161/OpenMontage

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

Army161/OpenMontage

Best practices for Remotion - Video creation in React

Army161/OpenMontage

Toolkit-specific Remotion patterns — custom transitions, shared components, and project conventions. For core Remotion framework knowledge (hooks, animations, rendering, etc.), see the `remotion-official` skill.

Army161/OpenMontage

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

Army161/OpenMontage

Animate SVG character rigs with GSAP, CSS transforms, Remotion frame control, and HyperFrames-compatible browser previews.

Verwandte Skills