Hey everyone! We just shipped the biggest update to OpenCut AI since launch, turning it from an AI-powered text editor into a full professional video editor. All open source, all self-hosted. Here's what's new: AI Features - AI Music Generation Pick a genre (15 options), mood (12 options), and tempo. Generate royalty-free background music and drop it on the timeline. - AI Thumbnail Generator Describe what you want or let AI generate from your transcript. 5 styles, 4 platform sizes, up to 4 variations at once. - AI Script-to-Video Write a script, AI generates voiceover, creates visuals, and builds the timeline automatically. - AI Auto-Duck Automatically lowers background music when speech is detected. Configurable duck amount and fade curves. - AI Auto-Color Correction 8 one-click profiles: Vibrant Pop, Film Look, Warm Sunset, Cool Blue, and more. Batch apply to all clips. - AI Video-to-Shorts One click to auto-select the best clip, trim to target duration, set 9:16/1:1/4:5 canvas, add subtitles. -Speaker-Labeled Captions Color-coded speaker labels, rename speakers, apply captions with speaker awareness. Professional Editor - 20 transitions Iris Wipe, Clock Wipe, Morph, Glitch, Film Burn, Page Peel, Cube Spin, and more. All WebGL shaders. - 12 effects + 22 filter presets Sharpen, Chromatic Aberration, Film Grain, Motion Blur, Duotone. Presets: Sunset Glow, Cyberpunk, Film Noir, Retro VHS. - Crop & Mask Rectangle, ellipse, polygon masks with feather and inversion. - Multicam Editing Sync angles, switch views with one click. - Marker System Colored markers with notes, jump between markers. - J/K/L Shuttle Playback Variable speed reverse and forward (1x-8x). - Ripple Trim Delete clips and close gaps automatically. - Compound Clips Nest multiple clips into one, un-nest anytime. Audio - Audio Effects Chain Per-track EQ, Compressor, Noise Gate, Reverb, De-esser, Limiter with Web Audio API processing. - Direct Recording Record audio from your mic directly to the timeline with live level metering. - LUFS Normalization Measure loudness and normalize to platform targets (YouTube, Spotify, Apple Podcasts, broadcast standards). - Beat Detection Detect BPM, visualize beats, snap edits to the beat grid. Workflow - Batch Export Queue up to 8 platform presets (YouTube 1080p/4K, TikTok 9:16, Instagram, Twitter, Podcast Audio). - Keyboard Shortcut Editor Full management UI with search, rebind, conflict detection. - Undo History Panel Visual command history, click to jump to any point. - Color-Coded Tracks 8 track colors + track locking. - Filmstrip Thumbnails Cached frame thumbnails on timeline clips. - Template Gallery 8 project templates (YouTube Intro, TikTok Vlog, Podcast Highlight, etc.). - Share via Link Generate share links with expiration and password protection. Why this matters Every other AI video editor (Descript, CapCut, Runway) sends your footage to the cloud. OpenCut AI runs entirely on your machine. No subscriptions, no data leaving your server, no per-seat pricing. Self-host on a $20/mo server or run it locally on your laptop or desktop. MIT licensed. What feature would you want us to build next?
OpenCut AI is the only self-hosted video editor with AI built in. We just added first-class support for MoonshotAI's Kimi K2 a 1T/32B active MoE model that runs entirely locally on TurboQuant.
What makes this different:
Kimi K2 handles natural language editing commands, script generation, and long-context video analysis all on your hardware
Three quantization tiers (Q3/Q4/Q5), so it runs on anything from a laptop to a GPU server
Kimi VL A3B adds vision-language understanding for scene analysis and multimodal commands
TurboQuant KV cache compression means you can run frontier-class models on 8 GB RAM