AI vocal remover and audio toolkit for separating vocals, instrumentals, and creating karaoke tracks
Free, open-source, node-based audio routing for macOS, Windows and Linux
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Free starter credits included with signup. One-time credit packs available for purchase. Monthly Pro membership with recurring credits and no daily limits; cancel anytime.
Free. Source code available under MIT license on GitHub.
Key features
Vocal and instrumental separation with AI
Batch processing up to 5 files for paid users
Stem splitting into 6 components
Support for multiple audio and video formats
Noise removal for podcasts and recordings
Text-to-speech with 300+ voices
Voice cloning from authorized recordings
AI music generation from text descriptions
Automatic BPM and key detection
Node-based audio routing graph
Unlimited virtual audio devices
System audio and per-app audio capture
Microphone capture with noise suppression, gate, compressor and EQ
CLAP, AU and VST3 plugin hosting
Multi-format recording including WAV, FLAC, AIFF, Opus, MP3, AAC
Audio streaming over network via WebRTC and UDP
Real-time resampling between different sample rates
What makes it different
Most 3-4 minute songs process in about one minute
Files automatically deleted after 3-30 days; no training on user uploads
Runs in browser without any download or plugin installation
Both free tools and AI tools with optional paid credits
Available as iPhone app with shared account and credit balance
Works on macOS, Linux and Windows with the same node graph approach
No kernel extension required on macOS
Open source under MIT license with full source code on GitHub
Includes built-in effects and supports third-party VST3, AU and CLAP plugins
Can record while routing audio in real time to multiple formats
VocalDock
Splitwave