AI video generator that creates realistic videos up to 30 seconds from text or images with native 4K resolution and synchronized audio
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Free
Freemium
Pricing
The Mac app is free. Local models have no per-request fees. Cloud providers using BYOK may charge their own fees.
Mini Plan: 3,000 credits per month (yearly); Standard Plan: 6,600 credits per month (yearly); Plus Plan: 14,400 credits per month (yearly); Pro Plan: 26,000 credits per month (yearly, 65% off limited time). Credits are used per generation based on resolution, output length and audio settings.
Key features
Chat with PDFs and get answers grounded in the document
Citations that follow back to exact pages
Offline PDF summaries with Local AI
Multi-document research across folders
Highlights and annotations with organization
Multiple export formats including HTML and PDF
Web share links for selected content
Generate videos from text prompts up to 30 seconds with 10 keyframes
Transform static images into dynamic videos with synchronized motion
Generate videos in multiple resolutions up to 4K with 16:9, 9:16 and 1:1 aspect ratios
Synchronized stereo audio and lip-sync for dialogue and performances
Support up to 15 reference assets including images, videos and subjects
Create videos in multiple visual styles including vlog, claymation, felt art and 3D cyberpunk
Generate dialogue in nine languages with multiple accents and dialects
Kling 4.0 Flash mode for faster iterations and frequent short-video creation
Multi-character reference images and character consistency across shots
Edit specific video sections, remove elements, or change visual style while preserving desired parts
What makes it different
Keeps PDFs and AI inference on your Mac for privacy
Citations and highlights keep research connected to sources
Works offline after model download
No account or document quota required
Up to 10 keyframes for directing character states, scene changes and emotional beats
Realistic motion with synchronized stereo sound and natural facial expressions
Support for 15 combined reference assets to guide consistent appearance and movement
Practical workflows designed for marketing, product storytelling and content production