InSplitter vs Open-Unmix

InSplitter is a browser service that uses AI to separate uploaded songs and videos into vocals, instrumentals, bass, drums, and other stems. Users can preview tracks in its player and download individual files or a complete bundle; separated output is WAV at 44.1kHz and 16-bit. It also provides vocal extraction, instrumental creation, pitch and speed controls, key and BPM detection, audio cutting and joining, and audio or karaoke recording. Listed inputs include MP3, WAV, FLAC, AAC, OGG, M4A, WMA, AIFF, MP4, AVI, MOV, MKV, WebM, FLV, and WMV. Demucs-based models support remixing, practice, and production workflows. The free plan permits files up to 50MB. Pro costs $15/month when billed annually or $19/month monthly, with files up to 500MB and batches of five. Uploads use HTTPS; results are deleted within 24 hours.

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.