AI video editor that makes edits from plain language descriptions
Reverse-engineer any video, shot by shot, to get a production blueprint
Stage
MVP
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Not given
Open-source and free to use offline. Optional third-party vision models (Gemini or Doubao) available for improved accuracy on re-compressed files; costs depend on the model provider's pricing, not Rea Video.
Key features
Natural language video editing - describe edits in plain text or voice
Activity panel shows every step - cuts, captions and titles visible as they happen
Automatic caption generation with brand styling
Quality check on every render against your brief
Policy engine with fixed rules - AI cannot override permissions
Batch editing - works on a file or a whole folder
Local processing - videos stay on your Windows 11 PC
Multiple output formats for different platforms
67 caption styles with 39 text animations and 2,020 fonts
Shot-by-shot production classification into 7 categories with confidence scores
Reverse-engineered prompts for AI-generated shots
Filming notes with camera, lens, and lighting setup details
Caption extraction with timings exportable as SRT/ASS
Audio analysis: voice, music, BPM, and sound-effect placement
98%+ shot classification accuracy on original files
Optional vision model integration for re-compressed files
Support for multiple video types: live-action, AI, 3D, code, avatar, screen recording, mixed
What makes it different
Describe edits in natural language instead of using complex timeline interfaces
Quality check reviews every render against your original brief before export
Policy engine ensures AI never makes unauthorized changes to your computer
All features available on every plan - pricing differs only in AI usage
Provides actionable remake plans instead of just binary AI/real labels
Tarzi
Rea Video