AIVoiceSeparator vs Demixr

AIVoiceSeparator separates songs into vocal and instrumental stems for backing tracks or clean vocals. Its Studio pipeline combines BS-Roformer, Mel-Roformer, and MDX23C, then applies EBU-R128 loudness normalization. The maker reports an SDR of 12.97 dB and says this is roughly 3 dB above the open Demucs baseline. The web app accepts audio and video files up to 100 MB and 20 minutes in formats including MP3, WAV, M4A, FLAC, OGG, WebM, Opus, and MP4/MOV. You can submit YouTube or SoundCloud links; TikTok clips must be saved and uploaded. Optional Whisper transcription returns SRT, LRC, and TXT files and adds about 30 seconds to processing. A REST API accepts a URL or upload and returns both stems. The free plan allows three songs per month when signed in; pay-as-you-go credits cost $0.50. The maker says uploads and results are deleted within 24 hours and audio is not used to train AI models.

Demixr is a web service for processing audio, with tools for separating vocals and instruments, removing reverb, marking speech, and analyzing BPM and key. Its Pro 1.5 vocal separation has Voice mode for complex mixes, live recordings, or speech over music, and Music mode for songs and covers or separating vocals from accompaniment. A separate stem tool uses Demucs to split music into vocals, drums, bass, and other parts. For dereverb, Demixr recommends isolating vocals first; applying the effect to a mixed track can cause artifacts or distortion. VAD provides editable speech-segment markers and batch export, though detection may be inaccurate with quiet vocals or noisy recordings. BPM analysis includes tempo, key, and Camelot values, with optional tap-to-sync. The free plan costs nothing and includes 10 minutes of audio monthly, a 10 MB upload limit, two VAD uses, queued processing, and no WAV downloads. Paid one-time plans start at $4/mo, without automatic renewal. Uploads and outputs are deleted within 24 hours by default.