Improved freemusicdemixer – AI music demixing in the browser
Hi HN, Last time I showed free-music-demixer, which people seemed to enjoy. It was a static website with a Javascript + WASM module to perform music demixing (or music source separation) using an AI model UMX-L (Open-Unmix) running client-side in the browser. Since then, I have overhauled the project and made several improvements: - The demixing/separation quality is higher now, since I implemented the missing post-processing step - Memory usage is lower now by performing a custom segmented inference with a streaming LSTM, which should allow larger tracks (or, dare I say,…
Improved freemusicdemixer – AI music demixing in the browser launched on September 14, 2023 with 160 votes, #294 of 4,228 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 3 years on.
In plain words
Improved freemusicdemixer is a browser-based tool that separates music into individual stems—vocals, drums, bass, and other instruments—using AI. It runs entirely client-side with no uploads required, processing audio through the UMX-L model. The latest version offers improved separation quality, reduced memory usage for handling longer tracks, batch processing of multiple files, and progress indicators. It's designed for musicians, producers, and anyone needing to isolate specific instruments from songs.
written from the facts on this page · September 2026
From the sources
Convert MP3 or WAV into editable sheet music and guitar tab drafts, MIDI, and stems, with specialized piano, drum, and guitar workflows.
Didn't receive it? Check the address for typos or use a different email. Enter your email to start Free Preview or continue checkout. Separate vocals, instrumentals, and six stems from the same upload. Piano and drums have the most specialized transcription paths. Use these for pitch drafts and cleanup. Piano and drum models are more specialized. Piano and drums have the most specialized transcription paths. Use these for pitch drafts and cleanup. Piano and drum models are more specialized. If you know the tuning, choosing it can improve results. Not sure? Standard is a good starting point. Sets the BPM for Original Timing MIDI while keeping it synced with your audio. Leave blank to use 120…from freemusicdemixer.com
In the maker’s words, at launch
Hi HN, Last time I showed free-music-demixer, which people seemed to enjoy. It was a static website with a Javascript + WASM module to perform music demixing (or music source separation) using an AI model UMX-L (Open-Unmix) running client-side in the browser. Since then, I have overhauled the project and made several…
Does a similar job
all alternatives →- FAFree AI-based music demixing in the browser2023 · sevag.xyz · ▲190
Hi all, I've spent some time working on music demixing or music source separation algorithms, which take in a mixed song and output estimates of isolated components (e.g. vocals, drums, bass, other). I took a popular PyTorch model with good performance (Open-Unmix, UMX-L weights), reimplemented the inference steps in C++, and compiled it to WebAssembly for a free client-side music demixer.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 24d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
