Transform text and images into high-quality videos with Wan 2.1 AI
Talk to your footage.
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Freemium
Pricing
BASE: $19.9/month with 20 credits per month; PREMIUM: $39.9/month with 50 credits per month; PRO: $79.9/month with 150 credits per month. All plans valid for 1 month.
Free: unlimited indexing and semantic search, exports capped at 720p with watermark, up to 60s. Reelary Pro: $79 USD one-time purchase, works on Mac and Windows, includes dialogue search, people recognition, places, team LAN sharing, full-resolution export (1080p/4K), FCPXML/EDL export, no watermark
Key features
Text to video generation with precise control over content and style
Image to video animation while preserving visual elements
Video editing with text prompts
Multiple specialized models including T2V-1.3B, T2V-14B, I2V-14B-720P, and I2V-14B-480P
Fast generation at 15 seconds per minute of content
High resolution video generation up to 1080P
Open source model with transparency and customizability
Support for English and Chinese text prompts
Text to image and video to audio capabilities
Multiple output formats: MP4, GIF, WebM
Semantic search across every frame of footage by meaning
Script-driven timeline that assembles matching shots automatically
Export MP4 with burned-in captions and AI voice-over
Export FCPXML and EDL projects for Premiere, Final Cut, DaVinci Resolve
Auto-reframe to 16:9, 9:16 and 1:1 aspect ratios
Dialogue search and transcription with Pro
People recognition and face grouping with Pro
GPS location mapping and city-based search with Pro
LAN team sharing to search from browser or mobile
MCP server and AI agent integration for Claude and Cursor
What makes it different
Open-source model with full transparency and community improvements
Fast generation speed significantly faster than traditional video production
Comprehensive media creation platform with text-to-image and video-to-audio
Support for both English and Chinese with cultural understanding
Multiple specialized models for different video generation needs
Exports finished MP4 with AI voice-over in one app instead of requiring a separate NLE
Searches by meaning across every frame, not just filenames or manual tags
Works with AI agents like Claude and Cursor to automate rough-cut assembly
Reelary