Learn how to use InterviewVision Analyzer to evaluate communication skills and technical abilities in interviews
Navigate to the Analyzer page and upload an MP4 or WebM video file (max 15 minutes). Optionally add a GitHub repository URL for code quality analysis.
Our AI will analyze the video for eye contact, speech patterns, pacing, screen sharing activities, and code quality. This typically takes 1-2 minutes.
View detailed metrics, timeline flags, screen activity analysis, code quality scores, and an overall assessment. Export or share the report.
Measures how often the candidate maintains direct eye contact with the camera.
Flags: Camera avoidance, hiding from view, excessive head turning
Analyzes words per minute (WPM) and pause patterns to assess speaking rhythm.
Flags: Rushed delivery, excessive pauses
Counts filler words like "um", "uh", "like", "you know" per minute of speech.
Custom filler words can be configured in Settings
Analyzes screen recordings to detect coding activities, tool usage, and productivity patterns.
Detects programming languages, frameworks, and productivity score
Reviews GitHub repositories for code quality, architecture, and best practices.
Analyzes up to 50 files for comprehensive quality assessment
Composite score combining all metrics with configurable weights.
Default weights: Eye Contact 35%, Pacing 25%, Fillers 20%, Engagement 20%
Uses MediaPipe Face Mesh for real-time facial landmark detection. Gaze direction and head pose are calculated from iris and facial geometry. Video frames are sampled every 1-2 seconds for efficiency.
Audio transcription uses the Web Speech API for browser-native processing. Filler word detection uses regex pattern matching on the transcript. WPM is calculated from total words divided by speaking time (excluding pauses longer than 2 seconds).
All processing happens client-side in your browser using Web Workers. Videos are not uploaded to external servers for analysis, ensuring privacy. Results can be exported as JSON for integration with other systems.
You can adjust analysis thresholds and scoring weights in the Settings page to match your hiring criteria:
Analysis results can be exported in multiple formats:
Structured data with all metrics, timestamps, and flags
Human-readable report with charts and highlights
Time-series data for custom analysis in Excel/Sheets
Send results to candidates or team members