Remove burned-in subtitles, captions and on-screen text from videos with AI, then add translated subtitles
Multimodal AI video generation platform for creators
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Free: 60 credits on signup (about 1 minute of Auto removal). Subscription plans: Basic $9.90/month (3000 credits), Standard $19.90/month (8000 credits), Pro $49.00/month (20000 credits). One-time packs: 600 credits for $4.99, 2400 credits for $14.99, 9000 credits for $39.99. Rates: Auto removal 1 cr
Basic Yearly: $24.99/month or $299.90/year, includes 2,500 credits per month, up to 110 seconds of video generation at 1080p resolution with sound effects and standard processing. Credit packs available for additional usage.
Key features
Automatic detection of captions in the lower half of the frame
Precise box drawing for any text removal anywhere in the frame
Background reconstruction without blur or black bars
Subtitle translation into 19 languages
Editable subtitles with SRT file downloads
Support for videos up to 10 minutes and 2K resolution
Original audio track preserved
No watermark on results
Text-to-video generation with natural language control
Image-to-video animation from uploaded or referenced images
Reference-guided video workflows with @tag system
Multi-shot continuity with consistent characters and environments
Advanced scene editing and seamless extensions
Audio-visual synchronization
First and last frame control with camera guidance
Multiple video model options including Seedance 2.5
Batch generation for up to 4 video variations
AI image generation tools for creative projects
What makes it different
AI reconstruction instead of blurring: rebuilds the actual background behind removed text
Two removal modes for different use cases: Auto for quick detection or Precise for exact control
Subtitle translation combined with removal in one workflow
Pay-per-second pricing with exact cost preview before processing
Combines multiple input modes—text, images, video, and audio—in one unified workflow for comprehensive creative control
Director-level control with reference guidance, frame control, and camera movement direction
Maintains visual consistency across multi-shot sequences and extended scenes
Seamless scene extension preserving motion and cinematic flow without restarting
Independent platform with automated content moderation and responsive support