AI studio for generating and editing images, videos, and 3D scenes with visual control
Convert video scripts from Instagram Reels, TikTok, YouTube and other platforms into readable text
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
Free: 1 transcript, then 3 per day with account. Starter pack: $5 for 30 transcripts (never expire). Creator pack: $12 for 100 transcripts (never expire). Pro: $9/month for 300 transcripts. Agency: $24/month for 1,500 transcripts.
Key features
Text to image generation with multiple AI models
Image to video generation
2D and 3D scene composition
Background removal and editing
Image to 3D mesh conversion
Character posing and identity transfer
Project saving and private library storage
Video timeline editing and frame extraction
Multiple AI video models with configurable parameters
Moodboard and reference organization
Support for Instagram Reels, TikTok, YouTube Shorts, Facebook videos and X (Twitter) videos
Automatic language detection without translation
Export as TXT, SRT or VTT formats with timestamps
One transcript covers videos up to 5 minutes
Free re-access to previously transcribed videos for 7 days
Failed transcripts cost nothing
Chrome extension available for desktop
Bulk processing for Agency plan up to 50 links at once
Download all transcripts as ZIP or CSV for Agency plan
What makes it different
Visual composition before AI generation - arrange your shot manually to establish intent before submitting to models
Free manual editing with credits only for AI operations - no charges for compositing, arranging, or saving projects
Integrated 3D scene composition within a single browser workspace
Access to diverse AI models including MiniMax, Seedance, Kling, and GPT Image
Built on authorized open-source creative tools with transparent attribution
First script is completely free with no account required
Pay-once credit packs never expire, no mandatory subscription
Works across five major video platforms in one interface
Transcripts processed in 5 to 20 seconds for most videos