AI that creates automated demo videos for web apps by recording walkthroughs from plain language guides
In-context image generation and editing with FLUX.1
Stage
Not given
Not given
Founded
Not given
Not given
Based in
EE
Not given
Pricing model
Paid
Freemium
Pricing
Starter: $49/month (approximately 20 minutes of video) or $490/year with 2 months free; Pro: $149/month (approximately 70 minutes of video) or $1,490/year with 2 months free; Team: from $399/month (approximately 200 minutes of video plus $2.00 per extra minute) or from $3,990/year with 2 months free
Free Tier at $0/month with 3 credits/month. Creator plan at $12.50/month with 100 credits/month. Professional plan at $33.33/month with 300 credits/month. Trial Pack available for $3 with 15 credits. 7-day money-back guarantee.
Key features
Plain language guide writing or AI-generated guides from source code
Automatic app sign-in with email and password credentials
17 language support with customizable voices
24 visual effects including highlights, zooms, tooltips and annotations
Branded opening and ending sequences with logo and colors
Desktop and mobile device recording (iPhone, Pixel, iPad)
Video exports including MP4, GIF, subtitles, chapters and thumbnail
Free guide checks before recording
Webhook integration and API access
MCP server integration for coding agents
Contextual image editing with targeted modifications to specific parts
Style transfer to transform images into artistic styles
Scene transformation to change environments while preserving subjects
Product visualization with template-based generation
Iterative refinement allowing multiple rounds of editing
Multi-modal input processing with text and images
Local editing to preserve rest of image while modifying specific elements
What makes it different
No manual video editing needed - guides are automatically converted to polished videos
Failed runs cost nothing, only finished video minutes are charged
Credentials never appear in videos - login happens in separate unrecorded browser
Native integration with coding agents via MCP server
Guides adapt to UI changes - buttons can move and labels can change without breaking
Up to 8x faster speed than leading models for image generation and editing
Accepts both text and image inputs for more coherent context-aware results
Maintains character and style integrity across different scenes
Targeted edits without affecting the rest of the image through text instructions
User-friendly interface making advanced AI capabilities accessible to everyone
Screen Browser
Kontext AI