First-round interviews don't scale. Recruiters lose days scheduling phone screens, every candidate gets different questions, and decisions come down to gut feeling — while great candidates accept faster offers elsewhere. InterviewCoach replaces the entire first round with a structured AI voice interview. An employer signs up, describes the role (JD, topics, pass score), and gets an AI-drafted question bank with scoring rubrics plus one auto-generated, shareable interview link. A candidate opens the link — no account, no scheduling — and talks to Talha, a live AI interviewer powered by the AssemblyAI Voice Agent API (real-time STT, managed LLM, TTS, barge-in). A video avatar listens while they speak and talks back; every answer is scored on clarity, depth, and STAR structure with instant spoken coaching. When the interview ends, the verdict appears immediately: beat the bar and a personal next-round pass link is auto-issued on the spot. Employers review transcripts, scores, pass rates, and passes in the hiring dashboard. Built with: AssemblyAI Voice Agent API (voice pipeline + turn detection), Python stdlib + SQLite backend (zero pip dependencies), Mistral AI question drafting with a role-aware local fallback, and a tool-call loop (get_question → evaluate_answer → get_session_summary).
Category tags: