AI tool that turns long videos into ready-to-post vertical clips with captions
Generative video models for animation
Stage
Startup
Not given
Founded
2026
Not given
Based in
US
US
Pricing model
Freemium
Not given
Pricing
Free trial: 10 processing minutes with no card required. Starter plan: $10/month (or $15 if billed monthly without yearly discount) includes 150 processing minutes, 1 connected social account, no watermark, extra usage $0.20/min. Pro plan: $20/month (or $30 if billed monthly without yearly discount)
Not given
Key features
Automatic highlight detection and moment selection
24-language support with language-specific typography
Word-by-word captions with karaoke timing
Two-speaker split-screen detection
Direct publishing to YouTube, TikTok and Instagram
Multiple output formats: 9:16, 1:1, 16:9
Automatic clip scoring and ranking
Silence trimming and gap removal
14 caption style options
Automatic title, hashtag and thumbnail generation
Pyramid-JiT (P-JiT) architecture with 32×32 token reduction
4× more aggressive token reduction than Linum v2
Converges in 11× fewer samples than Linum v2
2B-parameter model with frozen Qwen text encoder
Pixel-space diffusion with multi-resolution readouts
PixelREPA alignment with DINOv3-L
Curriculum learning over noise schedule
What makes it different
No watermark on paid plans, only on free trial
Language-native typography and Arabic dialect preservation
Per-minute pricing without credit packs or opaque systems
Finished output, not a timeline requiring further editing
Free trial requires no credit card
Low-cost training: full 2B model trained for just $21K in compute
Controls baked into model training rather than post-hoc fine-tuning
Pixel-space compression without separate VAE bottleneck
Apache 2.0 open release with full model weights and code
ClipFlap
Linum