Intelligent Sample Management and Processing

AI-Powered Bass Transcription & 3D Visualization. A Fullstack app converting audio stems to interactive tablature using Demucs, Basic Pitch, and React Three Fiber.

A user-friendly CLI wrapper for Demucs audio separation tool with automatic instrumental accompaniment generation.

Web-based voice editor — extract audio from YouTube, transcribe with word-level timestamps, edit with synced waveform + text UI, and remove background music with AI

Full-stack music learning web app featuring interactive guitar/piano tools and AI-assisted audio analysis (chord detection + vocal/instrumental separation)

A specialized system that converts raw guitar audio into accurate musical notation and tablature using a combination of digital signal processing and machine learning.

MCP server for AI music production — MusicGen generation, Demucs stem separation, RVC voice conversion. 8 tools, TypeScript.

🎵 AI-powered audio separation tool - Split any audio file into vocals, drums, bass, and other instruments using advanced machine learning. Built with React, Flask, and Facebook's Demucs v4 model.

Machine learning powered Karaoke app (with scores!)

Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, D3Net, Demucs, Tasnet, X-UMX. Built with React and Django.

The Open Source AI Musical Toolkit

Extract, transcribe, edit, and rearrange audio from YouTube or system output with synchronized waveform and AI-powered background removal.

OpenKara is an open-source desktop karaoke app that transforms your local music library into sing-along tracks using on-device AI stem separation and online synced lyrics, making karaoke affordable and reusable with the songs you already own.