AI speaker separation to split audio by speaker into individual tracks
Remove vocals from songs and videos to get instrumental and vocal tracks separately
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Free Trial: 20 credits once (about 2 minutes of Standard Separation). Monthly plans: Starter $12 (200 credits), Creator $29 (600 credits), Studio $65 (1500 credits). Annual plans: Starter $120, Creator $288, Studio $648. One-time credit packs: 200 credits for $16, 600 credits for $39, 1500 credits f
Free: 3 songs a day, full length as MP3, files up to 10 minutes and 100 MB, no sign-up. Pro: $4.99/month for up to 120 songs per month, WAV downloads, files up to 20 minutes and 200 MB. One-time Pack: $3.99 for 15 songs that never expire, WAV downloads, files up to 20 minutes and 200 MB.
Key features
Individual speaker tracks with separate WAV files
Time-aligned output with synchronized track starts
Automatic and manual speaker detection
Support for 30+ languages
Multiple audio and video file format support
Advanced Overlap mode for simultaneous speech
Private processing with 30-day result access
Preview functionality before download
Credit-based pricing with cost estimate before processing
Upload support for files up to 1 GB
Separate vocals and instrumentals from songs and videos
Full songs with no watermark or time limit
Process complete in about 30 seconds
Supports MP3, WAV, M4A audio and MP4, MOV video files
AI-based separation learns singing voice patterns
Preview and compare tracks before downloading
Extract music from video while keeping audio quality
Download as MP3 or WAV formats
Access download history page
What makes it different
Works with both audio and video files with automatic speaker detection
Handles overlapping and simultaneous speech with Advanced Overlap mode
Keeps time-alignment across all exported tracks for editing workflow continuity
Separates voices into individual tracks rather than just labeling speakers
Uses advanced AI model from Meta's Facebook AI Research instead of older stereo-cancellation techniques
No sign-up required for free plan
Works on mono recordings, not just stereo
Provides separate vocal track for practice and analysis
Works directly in browser without software installation
Seply
VoiceRemover