Piano-to-MIDI with Transkun, visualized in three.js using Gemini in Google Antigravity
alexanderchen · x · 2026-10-31
Alexander Chen shared a music-visualization workflow: transcribe raw piano audio to MIDI with the open-source Transkun, track hand positions, and visualize everything in three.js using Gemini inside Google Antigravity — capturing the feeling of "floating downward infinitely through space." An interactive prototype lets you scrub through time and explore.
Transkun is a neural semi-CRF piano transcription system (ISMIR 2024 / NeurIPS 2021 papers), installable via pip, with 500 stars on GitHub.
Related event: Developer Uses Gemini to Turn Piano Practice Into 3D Visualization(4 posts)→
More from coding & agent
- Engineer rates 10 kinds of work on 4 automation levels: only PM stays human — kieranklaassen · 2026-10-31
- Rewriting 5 agents as decision workflows: 20 seconds, 2 cents, 19/20 correct — generativist · 2026-10-31
- You May Not Need an Agent: Decision Workflows Did 20 Docs in 20s for 2 Cents — generativist · 2026-10-31
- Developer adds an AI assistant to GridCraft that runs app commands from plain English — dfinke · 2026-10-31
- Open-source iPhone shortcut lets Grok see your phone screen — Elon Musk amplifies it — elonmusk · 2026-10-31
- Someone gave Grok Bot a real phone line via Allo — Elon Musk retweets the demo — elonmusk · 2026-10-31