Vision & Listen
SMOG's intelligent Vision and Listen features help you interact with content through sight and sound.
Smart Features
Vision Feature
What Vision Can Do
- • Read screen text from any application
- • Identify UI elements like buttons and menus
- • Extract information from documents and websites
- • Understand context of what you're working on
- • Generate descriptions of visual content
- • Help with accessibility for visually impaired users
- • Provide smart suggestions based on screen content
- • Enhanced Quick Reply with visual context
Using Vision Feature
Activate Vision Mode
- • Use the shortcut⌘ + Shift + V
- • Click "Enable Vision" in Quick Reply interface
- • Say "SMOG, look at my screen" during voice commands
Vision in Action
Example: Email Reply
SMOG reads the email content and suggests contextual replies based on the email's content and tone.
Example: Document Summary
Ask SMOG to summarize a document and it will read the visible content to provide an intelligent summary.
Listen Feature
What Listen Can Do
- • Transcribe meetings in real-time
- • Capture audio notes hands-free
- • Listen to system audio (with permission)
- • Identify speakers in conversations
- • Generate meeting summaries automatically
- • Extract action items from discussions
- • Translate speech in real-time
- • Voice commands for hands-free control
Using Listen Feature
Start Listening
- • Use the shortcut⌘ + Shift + L
- • Click the microphone icon in the menu bar
- • Enable "Continuous Listening" in preferences
Listen Modes
Meeting Mode
Optimized for multiple speakers, generates structured summaries with action items.
Note Taking
Perfect for lectures, interviews, or personal voice notes with smart formatting.
Combining Vision & Listen
Multimodal Intelligence
When both Vision and Listen are active, SMOG provides the most comprehensive understanding of your context.
Smart Replies
Analyzes both what you're looking at and what you're hearing to craft perfect responses.
Context Awareness
Understands the full situation by combining visual and audio information.
Enhanced Accuracy
Cross-validates information from multiple sources for better results.
Privacy & Settings
- • All processing happens locally - your data never leaves your Mac
- • Selective permissions - choose which apps SMOG can see/hear
- • Temporary mode - enable Vision/Listen only when needed
- • Data retention - control how long transcripts and vision data are stored
Configure Vision & Listen Settings
Access Settings:
- 1. Open SMOG Preferences (⌘ + ,)
- 2. Go to "Vision & Listen" tab
- 3. Configure permissions, quality, and privacy settings
Key Settings:
- • Vision quality (Fast, Balanced, High Quality)
- • Audio processing (Real-time, Background, On-demand)
- • Privacy zones (exclude sensitive apps/areas)
- • Automatic features (smart suggestions, context hints)
Troubleshooting Vision & Listen
- • Check Screen Recording permissions in System Settings
- • Verify SMOG has Accessibility permissions
- • Try disabling and re-enabling Vision in SMOG preferences
- • Confirm microphone permissions are granted
- • Check input device selection in SMOG settings
- • Test microphone in other apps to rule out hardware issues
Ready to Explore?
Vision & Listen make SMOG incredibly powerful. Start with one feature and gradually enable both for the full experience.