{"id":47962645,"url":"https://github.com/scott-walker/video-crab","last_synced_at":"2026-04-04T10:00:56.667Z","repository":{"id":343535781,"uuid":"1178120541","full_name":"scott-walker/video-crab","owner":"scott-walker","description":"AI-powered video analysis \u0026 trimming tool. Transcribe with Whisper, analyze with Groq LLMs, narrate with ElevenLabs TTS. Desktop app built with Electron + SolidJS.","archived":false,"fork":false,"pushed_at":"2026-03-10T19:00:06.000Z","size":2788,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-11T00:02:27.366Z","etag":null,"topics":["ai","desktop-app","electron","elevenlabs","ffmpeg","groq","llm","open-source","solidjs","text-to-speech","transcription","video","video-analysis","video-editing","whisper"],"latest_commit_sha":null,"homepage":"https://scott-walker.github.io/video-crab","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/scott-walker.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-10T17:54:01.000Z","updated_at":"2026-03-10T19:00:13.000Z","dependencies_parsed_at":"2026-03-11T00:02:48.563Z","dependency_job_id":null,"html_url":"https://github.com/scott-walker/video-crab","commit_stats":null,"previous_names":["scott-walker/video-crab"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/scott-walker/video-crab","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scott-walker%2Fvideo-crab","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scott-walker%2Fvideo-crab/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scott-walker%2Fvideo-crab/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scott-walker%2Fvideo-crab/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/scott-walker","download_url":"https://codeload.github.com/scott-walker/video-crab/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scott-walker%2Fvideo-crab/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31395450,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T09:13:02.600Z","status":"ssl_error","status_checked_at":"2026-04-04T09:13:01.683Z","response_time":60,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","desktop-app","electron","elevenlabs","ffmpeg","groq","llm","open-source","solidjs","text-to-speech","transcription","video","video-analysis","video-editing","whisper"],"created_at":"2026-04-04T10:00:55.835Z","updated_at":"2026-04-04T10:00:56.645Z","avatar_url":"https://github.com/scott-walker.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://scott-walker.github.io/video-crab/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/scott-walker/video-crab/main/.github/logo.svg\" width=\"120\" alt=\"VideoCrab\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003e\u003ca href=\"https://scott-walker.github.io/video-crab/\"\u003eVideoCrab\u003c/a\u003e\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eAI-powered video analysis \u0026 trimming tool\u003c/strong\u003e\u003cbr/\u003e\n  \u003csub\u003eTranscribe, analyze, clip, and narrate — all from a single desktop app.\u003c/sub\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#features\"\u003eFeatures\u003c/a\u003e ·\n  \u003ca href=\"#quick-start\"\u003eQuick Start\u003c/a\u003e ·\n  \u003ca href=\"#configuration\"\u003eConfiguration\u003c/a\u003e ·\n  \u003ca href=\"#architecture\"\u003eArchitecture\u003c/a\u003e ·\n  \u003ca href=\"#license\"\u003eLicense\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## What is VideoCrab?\n\nVideoCrab is a desktop application for working with long-form video content. Instead of watching a 2-hour recording, drop it into VideoCrab and get a detailed, structured breakdown of everything that was discussed — with timestamps, topic segmentation, and suggested clips.\n\nBuilt with **Electron + SolidJS**, powered by **OpenAI Whisper**, **Groq LLMs**, and **ElevenLabs TTS**.\n\n## Features\n\n### Video Trimming\n- Drag-and-drop or file picker to load video\n- Visual waveform timeline with draggable trim handles\n- Click-and-drag range selection on the timeline\n- Precise timecode display (in/out/current position)\n- Clip management — save, name, and navigate between clips\n- FFmpeg-based export of trimmed segments\n\n### AI Transcription\n- Speech-to-text via **OpenAI Whisper API**\n- Per-region transcription — transcribe specific timeline segments\n- Transcript sidebar with clickable segments that seek to timestamp\n- Multi-language support (auto-detect or manual selection)\n\n### Semantic Analysis\n- **3-stage deep analysis** powered by Groq LLMs:\n  1. **Context extraction** — understands the overall topic, participants, and narrative\n  2. **Parallel chunk analysis** — detailed breakdown of 10-minute segments with full context\n  3. **Synthesis** — combines chunks into a cohesive, exhaustive analysis\n- Custom query support — ask about specific aspects (e.g., *\"Focus on financial decisions\"*)\n- Voice input for queries via microphone (Whisper-powered)\n- Analysis includes: summary, detailed chronological narrative, topics with timestamps, key moments, and suggested clips\n- Clickable timestamps in analysis results — jump to any moment\n- Progress bar showing analysis stages\n\n### Text-to-Speech\n- **ElevenLabs TTS** integration for reading analyses aloud\n- Section-based parallel fetching for fast playback start\n- Mini-player with play/pause, seek, skip ±5s controls\n- Per-analysis caching — instant replay without re-fetching\n- HTTP proxy support (CONNECT tunnel) for restricted networks\n\n### Project Management\n- Multiple projects with persistent storage\n- Auto-save with debounce\n- Transcript and analysis history saved per project\n- Region-based organization (multiple transcription/analysis sessions)\n\n## Quick Start\n\n### Prerequisites\n\n- **Node.js** 18+ and **npm**\n- **FFmpeg** installed and available in `PATH`\n- API keys for services you want to use:\n  - [OpenAI](https://platform.openai.com/api-keys) — for Whisper transcription\n  - [Groq](https://console.groq.com/keys) — for semantic analysis (free tier available)\n  - [ElevenLabs](https://elevenlabs.io/) — for TTS narration (optional)\n\n### Install \u0026 Run\n\n```bash\n# Clone the repository\ngit clone https://github.com/scott-walker/video-crab.git\ncd video-crab\n\n# Install dependencies\nnpm install\n\n# Run in development mode\nnpm run dev\n```\n\n### Build for Production\n\n```bash\n# Build and package\nnpm run dist\n```\n\n## Configuration\n\nOpen **Settings** (gear icon in the titlebar) to configure:\n\n| Setting | Description |\n|---------|-------------|\n| **OpenAI API Key** | Required for Whisper transcription and voice input |\n| **Groq API Key** | Required for semantic analysis |\n| **Groq Model** | LLM model for analysis (default: `llama-3.3-70b-versatile`) |\n| **Language** | Transcription language (auto-detect or specific) |\n| **ElevenLabs API Key** | For TTS narration (optional) |\n| **ElevenLabs Voice** | Voice selection (Rachel, Sarah, Adam, etc.) |\n| **Speech Speed** | TTS playback speed (0.7–1.2x) |\n| **ElevenLabs Proxy** | HTTP proxy URL for restricted networks |\n\nAll settings are stored locally in `~/.videocrab/settings.json`.\n\n## Architecture\n\n```\nsrc/\n├── main.js              # Electron main process\n│                        #   - FFmpeg audio/video extraction\n│                        #   - OpenAI Whisper API integration\n│                        #   - Groq LLM API integration\n│                        #   - ElevenLabs TTS with CONNECT tunnel\n│                        #   - Project file storage\n├── preload.js           # Secure IPC bridge\n└── renderer/\n    ├── App.jsx          # Root component \u0026 routing\n    ├── Editor.jsx       # Main editor (video player, timeline,\n    │                    #   transcription, analysis, TTS)\n    ├── Titlebar.jsx     # Custom titlebar with navigation \u0026 status\n    ├── Settings.jsx     # Settings panel\n    ├── ProjectPicker.jsx# Project list \u0026 creation\n    ├── store.js         # Global state (SolidJS signals \u0026 stores)\n    ├── format.js        # Time formatting utilities\n    └── global.css       # Complete design system\n```\n\n### Tech Stack\n\n| Layer | Technology |\n|-------|-----------|\n| Desktop runtime | Electron 33 |\n| UI framework | SolidJS 1.9 |\n| Build tool | Vite 6 |\n| Styling | Custom CSS design system (no frameworks) |\n| Transcription | OpenAI Whisper API |\n| Analysis | Groq Cloud (Llama 3.3 70B) |\n| TTS | ElevenLabs (Flash v2.5) |\n| Media processing | FFmpeg |\n\n### How Analysis Works\n\nFor long videos, VideoCrab uses a 3-stage pipeline:\n\n```\n┌─────────────────┐\n│  Full Transcript │\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ Context Extract  │  → \"This video is about X, participants are Y...\"\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│  Chunk Analysis  │  → 10-min chunks analyzed in parallel (max 5)\n│  ┌──┐┌──┐┌──┐   │     each chunk receives global context\n│  │C1││C2││C3│   │\n│  └──┘└──┘└──┘   │\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│   Synthesis      │  → Combined into single cohesive narrative\n└─────────────────┘\n```\n\n## License\n\n[MIT](LICENSE) — use it, fork it, build on it.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscott-walker%2Fvideo-crab","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fscott-walker%2Fvideo-crab","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscott-walker%2Fvideo-crab/lists"}