Turn any public webpage into a narrated MP4 video with AI
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Not given
Freemium
Pricing
Not given
Pay as you go with per-5-second credit pricing. Creator Monthly: US$29.99/month or US$14.99/month yearly (1500 rendering credits per month). Professional Monthly: US$79.99/month or US$39.99/month yearly (4400 rendering credits per month). Each 5 seconds costs 30 credits. Enterprise pricing available
Key features
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
Autonomous webpage reading and content extraction
8 art-directed visual presets plus custom style prompts
Duration control from 5 to 60 seconds in 5-second increments
Multilingual AI voices with voice previews
Synchronized SRT captions and subtitle export
Brand asset uploads up to 10 images of 8 MB each
Landscape 16:9 and portrait 9:16 aspect ratio support
Cloud background rendering with automatic credit refunds on failure
Deterministic frame-by-frame rendering on cloud workers
What makes it different
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
No desktop software installation required, runs entirely in browser
Intelligent content comprehension extracts core messages and hierarchy from webpages
Transparent per-5-second credit pricing with upfront cost estimates
Convert any public HTTP or HTTPS URL without login requirements
One-step localization into Spanish, Japanese, German, French or Chinese