Open-Unmix vs Sonura
Open-Unmix
github.comSonura
sonurastudio.comSide by side
| Figure | Open-Unmix | Sonura |
|---|---|---|
| Price from | Free | $10/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | Yes | — |
| Self-hosted | Yes | — |
| Plans published | 1 | 4 |
| Spec score · Stem Separation Software | 7.8 (#12) | 8.0 (#10) |
| Audio formats | The command line supports WAV, FLAC, and OGG files but not MP3; stempeg can expand supported input and output formats, including STEMS export. | The stem separator accepts WAV or MP3 uploads and returns stems as WAV or MP3. |
| Support | The project directs users to GitHub issues, Gitter chat, and Google Groups for technical help and support. | Sonura lists support by email or Discord; its pricing page includes priority 24/7 support on Pro and Max, plus one-to-one support calls on Max. |
Plans
In their own words
Open-Unmix
Open-Unmix is a PyTorch reference implementation for music source separation, aimed at researchers, audio engineers, and artists. Its ready-to-use models split pop music into vocals, drums, bass, and other instruments; a separate model, umxse, is for speech enhancement and was trained on the 28-speaker Voicebank+DEMAND corpus. Pre-trained choices include umxl, umxhq, umx, and umxse, with spectrogram variants also available. Each source model uses a three-layer bidirectional LSTM, a design the project says cannot run online or in real time. The code supports reproducing results, developing architectures, and adding data, while training is documented separately from the package. Install through pip or use the Docker container; pre-trained models can be loaded in Python or through torch.hub, and a Colab notebook supports online experimentation without local setup. The command line handles WAV, FLAC, and OGG, not MP3; stempeg can extend formats, including STEMS export. The software is MIT-licensed; umxl weights are non-commercial under CC BY-NC-SA 4.0.
Sonura
Sonura is an artist-led AI music studio for making loops, vocals, one-shots, stems, and full tracks in a browser or DAW. Its Sonura Split tool separates an uploaded mixed track into vocals and instrumental, or into six stems: vocals, drums, bass, guitar, piano, and other. It accepts WAV or MP3 uploads and returns stems in either format. Sonura says most tracks finish in under a minute, while longer files and six-stem splits can take a few minutes; processing runs on its machines. The page directs users to check the app for the current file-size limit but does not state the limit. For DAWs, Sonura Flow is a VST3 and AU plugin for Ableton Live, Logic Pro, FL Studio, Studio One, Bitwig, Cubase, Reaper, and GarageBand. It is available for macOS 12 Monterey or later and 64-bit Windows 10 or 11, and needs an internet connection while creating sounds. Sonura says stem splitting is cleared for commercial use if users own or have permission to use the recording. The free plan includes daily creation allowances; paid plans start at $20/mo.