CAD-Documenter

One video → Complete engineering documentation.

Transform video walkthroughs of CAD models into comprehensive, structured documentation — ready for CDRs, FEA setups, and client deliverables.

Features

• Smart frame extraction — Scene detection captures key moments, not every second
• Whisper transcription — Local GPU transcription, no cloud dependency
• Hybrid workflow — Export for Clawdbot processing (no API costs!)
• Windows GUI — Easy project management with CustomTkinter
• Atomaste PDF — Professional reports with engineering branding

Quick Start (GUI)

# Clone and install
git clone http://192.168.86.50:3000/Antoine/CAD-Documenter.git
cd CAD-Documenter
uv sync
uv pip install customtkinter

# Launch GUI
uv run cad-doc-gui

Workflow Options

Option A: Hybrid with Clawdbot (Recommended - No API Costs)

Windows (GUI)                  Clawdbot
─────────────                  ────────
1. Create project              
2. Add videos                  
3. Process --export-only       
   → FFmpeg frames             
   → Whisper transcription     
   → clawdbot_export/          
                    ─────────►
                               4. "Process CAD report for X"
                                  → Vision analysis (free)
                                  → Vault markdown
                                  → Atomaste PDF

Export for Clawdbot:

uv run cad-doc project init ./my-project -n "My Project"
uv run cad-doc project add ./my-project recording.mp4
uv run cad-doc project process ./my-project --export-only

Option B: Standalone with API

export OPENAI_API_KEY="sk-your-key"  # or ANTHROPIC_API_KEY
uv run cad-doc video.mp4 --bom --atomizer-hints --pdf

Installation

Requirements

• Python 3.12+
• FFmpeg
• CUDA GPU (recommended for Whisper)

# Windows (with chocolatey)
choco install ffmpeg

# Or download from https://ffmpeg.org/download.html

Install

git clone http://192.168.86.50:3000/Antoine/CAD-Documenter.git
cd CAD-Documenter
uv sync

# For GUI support
uv pip install customtkinter

CLI Reference

GUI

uv run cad-doc-gui

Project Management

# Create project
uv run cad-doc project init ./my-project -n "Project Name"

# Add videos
uv run cad-doc project add ./my-project video.mp4

# Process (export for Clawdbot)
uv run cad-doc project process ./my-project --export-only

# Process (with API)
uv run cad-doc project process ./my-project

# Check status
uv run cad-doc project status ./my-project

# Generate unified docs
uv run cad-doc project generate ./my-project

Single Video (API mode)

uv run cad-doc video.mp4 [options]

Options:
  -o, --output PATH      Output directory
  --frames-only          Only extract frames
  --skip-transcription   Skip audio transcription
  --atomizer-hints       Generate FEA optimization hints
  --bom                  Generate Bill of Materials
  --pdf                  Generate PDF output
  --api-provider TEXT    openai or anthropic
  --whisper-model TEXT   tiny/base/small/medium/large

Output

Clawdbot Export (clawdbot_export/)

<session>/
├── frames/           # Extracted keyframes
│   ├── 00-01-30.png
│   └── ...
├── transcript.json   # Whisper output with timestamps
└── metadata.json     # Session info

Full Processing

• 📄 Markdown — Structured documentation
• 📊 BOM — Components, materials, functions
• 🎯 Atomizer hints — FEA objectives & constraints
• 📑 PDF — Professional Atomaste-branded report

Tips

1. Narrate your recording — Audio narration = rich documentation
2. Collapse UI panels — In NX: Ctrl+Shift+N to hide Assembly Navigator
3. Use scene detection — Enabled by default, captures meaningful frames

Architecture

CAD-Documenter/
├── src/cad_documenter/
│   ├── cli.py              # Main CLI
│   ├── cli_project.py      # Project commands
│   ├── gui.py              # Windows GUI
│   ├── pipeline.py         # Processing orchestrator
│   ├── video_processor.py  # Frame extraction
│   ├── audio_analyzer.py   # Whisper transcription
│   ├── vision_analyzer.py  # AI vision (API mode)
│   ├── incremental.py      # Project processing
│   └── config.py           # Configuration
├── prompts/                # AI prompts
├── templates/              # Output templates
└── tests/

License

MIT

Credits

Built by Atomaste for the engineering community.