AI vocal remover online to separate vocals and instrumentals from songs and videos
Every book has a voice
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Free trial
Pricing
Free: 10 Credits for new accounts (expires after 30 days). 100 Credits: $4.99 (one-time, never expires). 250 Credits: $9.99 (one-time, never expires). 1 Credit per minute of audio.
7-day free trial on yearly and monthly plans. Unknown Pro: $49.99/year (best value), $4.99/month for 3,000 pages/month, or $2.99/week for 500 pages/week (no trial). Voice cloning: 1 free hour included with Pro subscription, then 3 hours for $4.99, 6 hours for $9.99, or 12 hours for $19.99 (one-time
Key features
Remove vocals from songs and videos in about a minute
Download as 320 kbps MP3 or lossless 44.1 kHz WAV
Support for MP3, WAV, FLAC, M4A, and video files up to 10 minutes
GPU processing on dedicated NVIDIA servers
Stem splitting with HTDemucs for four separate tracks
Karaoke tracks with adjustable guide vocal
Files encrypted during transfer and deleted after processing
Background music remover to remove music and keep speech
Vocal isolator to extract only the singer's voice
28 lifelike neural voices for narration
Synchronized paragraph highlighting with audio
OCR for scanned PDFs and textbooks
On-device AI chat with documents
AI-generated mind maps of document ideas
Multiple file format support
Focus sessions with calendar scheduling
Voice cloning with custom narration
Web reader accessible in any browser
Cross-device synchronization via iCloud
What makes it different
State-of-the-art Mel-Band RoFormer model preserves drums, bass, and stereo image unlike phase-cancellation methods
Fast GPU processing in 20 to 60 seconds instead of minutes
Pay only for successful separations with automatic refunds on failure
No subscription required with credits that never expire
Entirely on-device processing on Mac with no document uploads
Works offline after initial sign-in
Built by independent developer with privacy-first approach
Energy-efficient neural voices on Apple silicon
Focus sessions block distractions until reading is complete