Skip to content

01 - Quick Start Guide

⏱️ Time Estimate: 10-15 minutes
📋 What You’ll Learn: How to install Selfoss, activate your license, choose your privacy mode, create your first project, and process your first transcript



  1. Download the latest .exe installer from the Selfoss releases page
  2. Run the installer and follow the on-screen instructions
  3. Launch Selfoss from the Start Menu or Desktop shortcut
  4. ✅ The app will open with the Welcome Screen
  1. Download the latest .dmg file from the Selfoss releases page
  2. Open the .dmg file and drag Selfoss to your Applications folder
  3. Launch Selfoss from Applications (you may need to right-click → Open if macOS shows a security warning)
  4. ✅ The app will open with the Welcome Screen
  1. Download the .AppImage or .deb package from the Selfoss releases page
  2. For AppImage: Make it executable with chmod +x Selfoss.AppImage, then run ./Selfoss.AppImage
  3. For .deb: Install with sudo dpkg -i selfoss.deb
  4. ✅ Launch from your applications menu

💡 Pro Tip: Selfoss stores all your data locally on your device. No internet connection is required after installation (except for AI processing if using cloud providers).


Selfoss uses LemonSqueezy for secure license management.

  1. The Welcome Screen will appear when you first open Selfoss
  2. You’ll see two options:
    • Enter License Key (if you’ve already purchased)
    • Purchase License (redirects to purchase page)
  1. Enter your license key in the text field
  2. Click “Activate License”
  3. Wait for validation (requires internet connection)
  4. ✅ Success! You’ll see a confirmation message with your plan name
  5. The app will automatically take you to the main dashboard
  • View your license status in Settings → License Management
  • Deactivate on one device to move to another
  • Lifetime licenses include all future updates

⚠️ Important: Keep your license key secure. Each key can be activated on a limited number of devices simultaneously.


Selfoss offers flexible privacy options to match your needs:

Section titled “🔒 100% Local Mode (Recommended for Privacy)”

Best for: Maximum privacy, no cloud dependencies, unlimited free usage

What you need:

  • Ollama installed locally (for text analysis)
  • Whisper.cpp models downloaded (for transcription)

Benefits:

  • ✅ Zero cloud API calls
  • ✅ Complete data privacy
  • ✅ No ongoing costs
  • ✅ Works offline

👉 Setup Guide: See 02_PRIVACY_FIRST_SETUP_GUIDE.md

Best for: Fast processing, no local setup required

What you need:

  • OpenAI API key OR Google Gemini API key
  • Internet connection

Benefits:

  • ✅ Fastest processing
  • ✅ No local model downloads
  • ✅ State-of-the-art AI models
  • ❌ Pay-per-use API costs

👉 Setup Guide: See 03_CLOUD_PROVIDER_SETUP_GUIDE.md

Best for: Cost optimization and flexibility

Example configurations:

  • Local transcription (Whisper.cpp) + Cloud analysis (OpenAI GPT-4)
  • Cloud transcription (OpenAI) + Local analysis (Ollama)

👉 Setup Guide: See 13_ADVANCED_WORKFLOWS_GUIDE.md

💡 Pro Tip: Start with Cloud Mode for quick testing, then switch to Local Mode for privacy and cost savings.


Projects help you organize transcripts by topic, team, or time period.

  1. Click the ”+ New Project” button in the left sidebar
  2. Fill in the project details:
    • Name: e.g., “Marketing Team Meetings”
    • Description: Optional details about the project
    • Color: Choose a color tag for visual organization
  3. Click “Create Project”
  4. ✅ Your new project appears in the sidebar
  • 📁 Use projects for different teams or meeting series
  • 🎨 Color-code related projects (e.g., all engineering projects in blue)
  • 📝 Add descriptions to help remember project context

Keyboard Shortcut: Press Ctrl+B (Windows/Linux) or Cmd+B (macOS) to toggle the sidebar

👉 Learn More: See 04_PROJECT_WORKSPACE_MANAGEMENT_GUIDE.md


You can create transcripts in two ways: Upload a file or Record audio.

  1. Select your project in the sidebar
  2. Click “Upload & Process” button in the header
  3. Choose your file:
    • Supported formats: .txt, .docx, .vtt, .srt
    • File size: 1KB - 50MB
    • Must be UTF-8 encoded
  4. Wait for validation (automatic)
  5. Click “Process with LLM”
  6. Configure AI settings (first time only):
    • Select your provider (OpenAI or Gemini)
    • Enter your API key
    • Choose a model
  7. Click “Start Analysis”
  8. ✅ Watch the progress indicator as AI processes your transcript
  9. View results: Decisions, actions, and concepts are displayed

⏱️ Processing Time: 10-30 seconds for typical meeting transcripts (depending on provider and file size)

👉 Detailed Guide: See 06_TRANSCRIPT_UPLOAD_PROCESSING_GUIDE.md

  1. Select your project in the sidebar
  2. Click the microphone icon 🎤 in the header
  3. Allow microphone permissions (browser will prompt)
  4. Click “Start Recording”
  5. Speak or capture your meeting
  6. Click “Stop Recording” when done
  7. Transcription (automatic if enabled):
    • If auto-transcribe is ON: Automatically processes
    • If auto-transcribe is OFF: Use “Transcribe Audio” button later
  8. ✅ Your recording appears in the transcript list

⏱️ Transcription Time: Varies by provider (OpenAI: ~30 seconds, Ollama: 2-5 minutes for 1 hour)

👉 Detailed Guide: See 05_AUDIO_RECORDING_TRANSCRIPTION_GUIDE.md


Windows: “Windows protected your PC” warning

  • Click “More info” → “Run anyway”
  • This is normal for apps without Microsoft code signing

macOS: “App is damaged” or “Can’t be opened”

  • Run: xattr -cr /Applications/Selfoss.app
  • Or right-click → Open (first time only)

Linux: AppImage won’t run

  • Make it executable: chmod +x Selfoss.AppImage
  • Install FUSE: sudo apt install fuse libfuse2 (Ubuntu/Debian)

“Invalid license key” error

  • ✅ Check for typos or extra spaces
  • ✅ Ensure you’re using the key from your purchase email
  • ✅ Check your internet connection

“Maximum activations reached”

  • Deactivate Selfoss on another device first
  • Go to Settings → License Management → Deactivate

Recording produces empty transcript

  • ✅ Check microphone permissions in system settings
  • ✅ Verify audio input is working (test in other apps)
  • ✅ Ensure recording duration was at least 5 seconds
  • ✅ Check API key is valid (for cloud providers)

Uploaded file fails processing

  • ✅ Verify file format is supported (.txt, .docx, .vtt, .srt)
  • ✅ Check file size is between 1KB and 50MB
  • ✅ Ensure file is UTF-8 encoded
  • ✅ Try opening file in text editor to verify content

“API key invalid” error

  • ✅ Verify you entered the correct API key
  • ✅ Check API key has sufficient credits/quota
  • ✅ Ensure API key is active in your provider account

“Connection timeout” error

  • ✅ Check your internet connection
  • ✅ Verify provider’s API status page
  • ✅ Try a different model (some are faster)

👉 Full Troubleshooting Guide: See 12_TROUBLESHOOTING_FAQ_GUIDE.md


Congratulations! 🎉 You’ve completed the Quick Start Guide.

  1. 🔒 Set up privacy-first mode02_PRIVACY_FIRST_SETUP_GUIDE.md
  2. 📊 Learn about visualizations07_VISUALIZATION_DEEP_DIVE_GUIDE.md
  3. ✏️ Try interactive editing08_INTERACTIVE_EDITING_GUIDE.md
  4. 🔍 Master global search11_SEARCH_DISCOVERY_GUIDE.md
  5. 💾 Set up backups09_DATA_MANAGEMENT_GUIDE.md
  • Keyboard shortcuts for faster workflows
  • Custom widget ordering to prioritize your views
  • Batch processing for multiple transcripts
  • Hybrid privacy setups for cost optimization

Happy transcribing! 🚀