AI song generator that creates complete songs from prompts or lyrics
2K video with native stereo audio in one pass
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
On the Hailuo AI App: free tier and paid monthly plans (rates listed in app). On MiniMax Open Platform: billed per output second, with 2K tier priced above 768p tier. On this site: 18 credits per second at 768p and 29 credits per second at 2K, with annual plans showing 50% discount and various month
Key features
Generate complete songs with vocals from text prompts or lyrics
Create instrumental versions for background music and videos
Generate two song versions in one request to compare results
Support for multiple languages and styles (pop, hip-hop, rock, electronic, jazz, etc.)
Production in minutes with automatic composition, arrangement, and mixing
Commercial license included on paid plans
Full flexibility to edit generated songs in any DAW
Private generation option to keep songs hidden from public gallery
Fast mode with priority access and no watermark on paid plans
Multimodal reference input: images, video, and audio
Context-IR token-based pricing variant
Downloadable weights for local deployment
H3-Contextual Omni Representation for modality bridging
Up to 12 reference files with caption compression
What makes it different
Generates complete broadcast-ready tracks with automated composition, arrangement, mixing, and mastering in minutes
Accepts input in multiple languages for global user base
Generates two versions per request for comparison and selection
Free trial with 10 credits and no credit card required
Commercial license included on paid plans for monetization rights
Only model generating video and audio together natively
2K output at lower per-second rate than competitors
Downloadable open weights available
Accepts richer multimodal reference input than competitors
GenSong
MiniMax H3