Analyze once, render instantly. 100% on your device with OPFS cache, optional vocal melody extraction, and optional local auto-lyrics.
Drop in an audio or video file, analyze it locally, and export tabs, sheet-style output, structured JSON, or timed VTT cues. This page is built for quick iteration and future upgrades.
We can auto-transcribe lyrics fully on your device. We’ll help set up a tiny local tool
(Python + Whisper) and connect to it at http://127.0.0.1:8765. Nothing leaves your computer.