Built like a studio tool given away free.
Fast and Max models
The RoFormer model family UVR5 uses, offered at two qualities. Fast for a quick pass, Max when the mix is dense.
Both stems, one pass
The isolated vocal and the instrumental land together in the Results feed — separation is one job, not two runs.
Video too
Drop a music video or a movie clip; the audio is extracted, separated, and the stem you chose is re-muxed back in sync.
Fully scriptable
Everything the app does works from the CLI, with --json output for pipelines. Right-click Quick Actions on macOS into the bargain.
Two passes, depending on the mix.
VocalDrop is built on the RoFormer separation models, run locally through audio-separator. Which one runs is the only choice the app asks you to make.
Drop the file in
Audio or video, one or a queue. Video is de-muxed, separated, and can be re-muxed back in sync with whichever stem you kept.
Fast — a single pass
One high-SDR BS-Roformer pass. Near real time on Apple Silicon, and enough for a clean source.
Max — three models, blended
Three RoFormer checkpoints run and their vocal estimates are weighted together, then de-reverbed and de-noised. Slower, and the one to reach for on a dense mix.
Both stems land together
The vocal and the instrumental come out of the same run, so a karaoke bed costs nothing extra.
Against the usual suspects the ones that upload your audio.
| Compared on | VocalDrop | Online tools | UVR5 | Moises | iZotope RX |
|---|---|---|---|---|---|
| Files stay on your machine | yes | no — uploads | yes | no — cloud | yes |
| Free | yes | limited tier | yes | paid | paid, dearly |
| Native desktop app | yes | browser only | no — Python GUI | yes | yes |
| No watermarks or quotas | yes | no | yes | no | yes |
| Apple Silicon GPU (Metal) | yes | n/a | manual setup | yes | yes |
| No account | yes | often required | yes | required | yes |
vocaldrop vocals song.mp3 --quality maxEvery option the app exposes, with --json for pipelines.
Your audio never leaves the machine — and the diagnostics that do.
Most free vocal extractors are websites that upload your audio to someone else's server. VocalDrop runs the models locally on your own CPU or GPU, so the audio is never sent anywhere, and there is no track limit, watermark or subscription attached to the decision.
What does leave the machine, stated plainly: anonymous crash and usage diagnostics — never file contents, never paths, never personal data — the one-time engine and model download on first launch, a URL if you paste one in for the app to fetch, and the update check if you leave it on. That is the complete list.
Questions
What model does it use?
The RoFormer family, the same architecture UVR5 ships, run through audio-separator — as a native desktop app, with no Python setup and no dependency roulette. Fast is a single pass; Max is a three-model ensemble, blended and cleaned up.
Is it really free?
Yes. Free to use, with no watermarks, no track limits, no feature paywall and no account. It is closed source; the public repository holds the downloads and the README.
Does it need the internet?
Only on the first launch, which downloads the engine and models once — about 2 GB for the full set, or roughly 200 MB if you only ever use Fast. After that separation is entirely offline.
What about my files?
They are processed on your machine and never uploaded. VocalDrop does send anonymous crash and usage diagnostics — never file contents, file paths or personal data — and the only other network calls are the one-time model download, a URL you paste in yourself, and the optional update check.
Which Macs and PCs?
Apple Silicon Macs (M1 to M4), Windows 10 or 11 on x64, and Linux on x64. Intel-Mac builds are not provided. Separation is GPU-accelerated through Metal on Apple Silicon; Windows and Linux run on multi-core CPU, which is slower but just as offline.
Why does my Mac say it cannot open it?
The current builds are not code-signed or notarized yet, so Gatekeeper objects on first launch: right-click the app and choose Open. On Windows, SmartScreen wants More info, then Run anyway. Signed builds are on the roadmap.
Can I automate it?
Yes — a full CLI ships inside the app and mirrors everything the interface does, with --json output for pipelines. macOS also gets right-click Quick Actions in Finder.
The vocals come out, and nothing goes up.
Separation runs on your own CPU or GPU, so the track never leaves the machine and there is no queue to wait in. One download for macOS, Windows and Linux.
Download — macOS, Windows, LinuxFree · macOS, Windows and Linux
VocalDrop