SyntaxCue is a local-first AI interview copilot that captures live interview audio, transcribes it on-device using whisper.cpp, and streams answer suggestions without recording or uploading audio. The article details the complete technical pipeline across macOS and Windows, including system audio capture via CoreAudio Process Tap and WASAPI loopback, voice-activity detection, local transcription, and LLM response streaming.
A coding interview practice platform offering multi-step questions that simulate realistic interview scenarios with evolving requirements, similar to LeetCode but with follow-ups and time pressure. Supports Python and TypeScript, runs locally in the browser for privacy, and offers both free and premium questions with persistent progress tracking.