Turn one line into a complete song with lyrics, vocals and arrangement
PDF and image translator that preserves layout
Stage
MVP
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Freemium
Paid
Pricing
Free tier available. Paid plans: Basic at $14.90/month (1,000 credits/month) and Premium at $32.90/month (3,000 credits/month). Save up to 51% with yearly billing.
Pay-as-you-go credit system. New accounts receive 5 cleanup pages + 5 translation pages automatically. Larger top-ups add more credits per dollar. Custom top-ups are billed in USD. Credit packs currently unavailable; visit billing to add credits.
Key features
Text to full song generation from mood, memory or story
Smart lyrics generation and optimization in Chinese or English
Reference audio for style transfer
Style transfer to reimagine audio in new genres
Music recipes showing prompts behind each song
Scene presets for moods like late-night emo, workout, sleep, coffee-afternoon and focus
Community plaza to publish, discover and engage with AI-generated music
Extend music seamlessly up to 8 minutes
WAV export for high-quality lossless audio
Vocal removal with 2-stem or multi-stem splitting
Translates PDFs, JPEG, PNG, and WebP formats
Supports 100+ languages
Layout preservation with OCR
Built-in editor for corrections
Style reference pinning across pages
Page-to-page context for consistency
Web and desktop app availability
Local project storage by default
What makes it different
End-to-end full-track generation planning lyrics, melody, arrangement and vocals together in one pass
Deep understanding of both professional music terminology and everyday language
Strong control over vocal gender, singing style, key, BPM, instrumentation and emotional progression
Commercial licensing available with credits-based usage system
Preserves original layout and design while translating
Maintains character names and voice across consecutive pages
Review and edit each translated page before exporting
Pay-as-you-go pricing with no subscriptions
Works on full batches rather than individual pages