Turn screen recordings into step-by-step guides with screenshots
AI image and video generator with text-to-image, image editing, and video creation in one workspace
Stage
MVP
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Paid
Pricing
Personal: Pay-as-you-go credit packs - Starter $7 (10 credits), Basic $12 (25 credits), Pro $20 (50 credits), Plus $35 (100 credits). Credits never expire. Team: $79/month during early access (regular price $99/month), includes up to 20 seats, 100 credits per month renewed each cycle, 4 roles, manda
Not given
Key features
Works without audio narration
Built-in Markdown editor with live preview
Team workspaces with roles and MFA
Support for MP4, MOV, AVI, WebM up to 10 minutes and 250 MB
In-browser screen recording without extension or install
Export as Markdown, HTML, or PDF
Multiple AI models to choose from
EU infrastructure with video deletion after processing
Text-to-image generation from written prompts
AI image editing with instruction-based changes
Text-to-video generation for scene descriptions
Image-to-video animation with controlled motion
First-and-last-frame video generation
MP4 video extension for supported source videos
Background task processing without waiting
Private image and video history in My Creations library
Flexible output settings for aspect ratios and resolutions
Transparent credit costs shown before submission
What makes it different
Automatic screenshot selection and step descriptions from video without manual capture
Works without narration by analyzing visual screen changes
Fast processing: 5-minute recording typically becomes a guide in 2-4 minutes
One-click translation into 35 languages
Free trial with 10 credits and example project, no credit card required
All image and video tools in one focused workspace without switching pages
Background generation lets you start new tasks immediately while others process
Transparent credit pricing with exact costs shown before each generation
Supported source formats include text, images, keyframes, and MP4 videos
Prompt-aware workflows expose only relevant inputs and settings for each mode
video2docs
Flux-3-Pro AI