v0.1.0 — Initial Open-Source Release
Aural v0.1.0 — Initial Open-Source Release
The first public release of Aural, an open-source AI interview platform for voice, chat, and video.
Highlights
- AI-Powered Interviews — Describe your goals in plain language and Aural generates a complete interview with questions, criteria, and scoring rubrics.
- Voice, Chat & Video — AI-driven interviews across all channels with real-time adaptation and follow-up questions.
- Live Coding & Whiteboard — Monaco editor and Excalidraw whiteboard built in for technical assessments.
- Automated Reports — Per-question scores, highlights, and improvement areas generated by AI when the session ends.
- Anti-Cheating — Tab monitoring, paste blocking, multi-screen detection, and integrity logs.
- Team Management — Organizations, projects, and role-based access control.
- Multilingual — English and Chinese with a pluggable locale system.
- Pluggable LLMs — OpenAI, Moonshot Kimi, MiniMax, or any OpenAI-compatible API.
- Self-Hosted — Run the full stack locally with Docker, Supabase, and Node.js.
Tech Stack
- Next.js 14 (App Router) + TypeScript
- Supabase (PostgreSQL + Auth)
- tRPC for type-safe APIs
- WebSocket voice relays (Kimi, OpenAI, Azure, Doubao)
Getting Started
See the Self-Hosted deployment guide in the README.