VocalSplit – Browser-based vocal remover running 100% locally
WebAssembly ML inference beats server-based tools like vocalremover.org on privacy.

Runs vocal separation and transcription locally on Apple Silicon, no subscriptions required.
Karaoke enthusiasts, content creators, singers
Moises.ai · Vocalremover.org · Singa
I like karaoke and I grew up with the Asian style karaoke with the music video behind and the karaoke lyrics at the bottom.
Sometimes I want to do a song and there is no karaoke version video like that.
A few years ago I came across ML models that cleanly separate the vocals and the instrumental music of a song. I thought of the idea to chain together ML models that can take an input music video file, extract the audio (ffmpeg), separate the tracks (ML), transcribe the lyrics (ML), burn the lyrics back with timing into the video (ffmpeg), and output a karaoke version of the video.
This is an early version of the app, Mac only so far (since I use Mac, despite it being an electron app.. I do eventually want to make a Windows build), I've only let a few friends try it. Let me know what you think!
WebAssembly ML inference beats server-based tools like vocalremover.org on privacy.
Text or an image -> a studio-style song with auto-generated lyrics and even a SynthID authenticity watermark; that's the product pitch and it's compelling in one line. The site bundles sensible add-ons (AI video maker, vocal remover, lyrics tool) that nudge it from a novelty toward a usable toolkit, but the space is crowded and the integration is still 'coming soon,' so the real test will be fidelity of Lyria 3 outputs and licensing/rights details.
Music stem separation in the browser without uploads—Rust + WebGPU beats cloud dependency.
This is a music video, not a software project — wrong venue for Show HN.
Another AI music generator when Suno and Udio already dominate.
Another AI music video generator in a crowded Kaiber and Pika landscape.