AI video generator for text-to-video and image-to-video creation
AI image translator that translates text in images while preserving the original layout
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Pay as you go or subscription plans. Starter: $9.9/month ($119/year, 800 credits/month, cost per 100 credits $1.24). Premium: $19.9/month ($239/year, 2,000 credits/month, cost per 100 credits $1.00). Advanced: $49.9/month ($599/year, 6,000 credits/month, cost per 100 credits $0.83). All subscription
Not given
Key features
30-second native video generation in one continuous clip
Up to 10 keyframes for precise shot control
Up to 15 multimodal references in a single generation
Stereo audio and accurate lip-sync
Stable large-scale camera motion
Precise video editing with subject and background control
Creative remake from reference videos
8,000-token prompt understanding
Multiple language and accent support
Commercial use license on subscription plans
Batch image translation
AI-powered text recognition in images
Original layout preservation while translating
Multiple language support
Watermark-free translation option
Commercial use license for paid plans
Private generation of translations
Faster generation speed for paid users
High quality image output
What makes it different
Generates 30-second continuous native video instead of stitched short clips for coherent long-form storytelling
Combines multiple image and video references with subjects in a single generation to maintain consistency with fewer retries
Uses 8,000-token prompts with director-style shot decisions to turn detailed scripts into complete stories
Faster Kling 4.0 Flash variant for high-volume creation with lower cost per video
Preserves original image layout while translating text
Works with diverse image types including comics, screenshots, menus, and product labels
No need to manually copy text before translating
Batch processing allows translating multiple images at once
Professional-quality results with context-aware translation