• Integrated AI Models:
    • Local Generation: Local Stable Diffusion (Nvidia/CUDA, Z-image, Flux2, Flux 2 klein etc), Local video generation (FramePack integration, WAN 2.2).
      • Local VibeVoice TTS 0.5B, 5B and 7B & Chatterbox for TTS (text-to-speech), both includes voice cloning
    • Online Image Services: Supports BFL Flux 1 & 2, Luma Labs DreamMachine, Runway ML, Qwen, WAN, Google nano banana, FAL AI API.
    • Online Video Services: Integration with Luma Labs, RunwayML, Minimax, KlingAI, Google Veo, Fal AI.
    • Online Audio Services: ElevenLabs, Resemble AI / Chatterbox, Minimax.
  • AI Enhancement Tools:
    • Upscaling: Image & Video upscaling.
    • Interpolation: Frame interpolation (increase video framerate).
    • Prompt Engineering: LLM (Large Language Model) integrated to convert lyrics to descriptive prompts (Mistral AI, OpenAi and Google Ai integration).
      • Local LLM’s supported also!
  • AI Asset Management: Fast AI video creation using lyrics to generate still images; Media Library support to store GenAI materials across projects.

  • Import & Sync:
    • Easy and fast lyric import (supports .lrc, .vtt, .srt, .tsv).
    • AI Transcription: Export lyrics from audio via local Whisper-integration, ElevenLabs API or OpenAI API.
      • Extract vocals from background / stem separation
    • Sync Tools: Word-by-word offsetting, automatic lyric lining for long lines, tempo snap mode, manual sync mode (sync as you play).
  • Text Styling & Effects:
    • Typography: Gradient colors & blend modes for fonts, text backgrounds, 3D text support.
    • Karaoke & Transitions: Karaoke mode, letter-by-letter transitions, timer & countdown support.
    • Editing: Split text items easily, automatic opacity cross-fades for overlapping items.
    • Manipulation: Animate properties. Modulate animation strength with audio volume!

  • MilkDrop Engine: 8000+ presets (downloadable/customizable), audio-reactive backgrounds without screen recording (and without AI).
  • Audio Integration:
    • ASIO Support: Low latency recording for advanced audio systems.
    • Live Input: Record audio and video to timeline simultaneously.
  • Advanced Visuals: Fragment Shader support (GLSL to SKSL converter), presets for plugins and primitives.

  • Speed & Automation:
    • Automatic Silence Removal: Automatic trimming based on audio volume. Remove silent parts from video fast (Jump-cut automator).
    • Auto-Subtitles: Export text from audio with local Whisper-integration. Perfect for adding captions to talking-head videos.
    • Project Wizards: Project Start Wizard to get you started easily.
  • Format & Repurposing:
    • Social Ready: Export any resolution videos (Vertical 9:16 for TikTok/Reels/Shorts, Square 1:1, or Widescreen).
    • Bulk Manipulation: Image cropping in bulk (great for resizing assets for different platforms).
    • Upscaling: Image & Video upscaling (turn old footage into 4K content).
  • Branding & Workflow:
    • Reusable Assets: Project import for re-using materials (intros, outros, end-cards).
    • Asset Management: Media Library support to store GenAI materials across projects.
    • Pricing: Flexible! Buy once, keep getting the updates! Or, enhance your LITE version with monthly subscriptions

  • Timeline & Tracks:
    • Multi-track timeline (audio, video, lyrics, AI content).
    • Drag & drop media directly from OS folders.
    • Non-linear editing with basic and advanced trimming (split, loop, speed alternation).
  • Visual Effects (VFX):
    • Motion & Color: Object detection and motion tracking, Color transfer/matching (fine-tune matrix), Chroma key removal, masking, and background removal (RemBg).
    • Transitions: 91 crossfades/transitions; animate almost any value of text, images, and videos.
  • Manipulation: Image cropping (bulk), video clipping/trimming, upscaling / downscaling / interpolation.

  • Project Management:
    • Project Start Wizard, Storyboard mode (grid view).
    • Project archiving (Zip) and cloud sharing (Dropbox, Google Drive integration).
    • Project import (re-use intros/outros).
  • Connectivity:
    • SPOUT Support: Record from Spout input OR send playback to Spout.
    • Hardware: Multi-monitor support (detachable render view).
  • Usability: Copy-paste text/files from OS to timeline, edit/move multiple items at once, duplicate tracks.

  • Export Options:
    • High Quality: 4K support, export any resolution.
    • Formats: Transparent export rendering (PNG frames), export single frames.
    • Performance: Multithreaded off-screen video export rendering.
  • Markers: Start & end markers, custom project rendering markers.
  • Licensing: “From musician to musicians” philosophy—No monthly fees (Pay once, keep forever).
    • Separate Free LITE version available: choose your own features for monthly subscription

Full list of features

  • Non-linear editing with AI image and video sources
    • European alternative for professional video editing software!
  • Local Stable Diffusion (Nvidia / cuda, also cpu), video generations provided by online service providers
  • Record audio and video to timeline
    • ASIO support for low latency recording for advanced audio systems. Record video simultaneously
  • MilkDrop visualizations: Create audio-reactive backgrounds. Remember the good old times with Winamp? Now you can use the same presets to visualize your music without extra screen recording apps. Finally, software that really whips the LLaMA’s ass.
    • 8000+ presets, downloadable separately. Add your own presets as well!
    • Future updates will bring in advanced playlist editing
    • See the landing page
  • SPOUT support: Record from Spout input OR send your playback to spout input
  • Supports online image generations services (BFL Flux 1 & 2, Luma Labs DreamMachine, Runway ML, Qwen, WAN, Google nano banana, FAL AI API and many more!)
  • Supports online video generation services: Luma labs, RunwayML, Minimax, KlingAI, Google Veo, Fal Ai with tens on different models!
  • Support online audio generation services: ElevenLabs, Resemble AI / chatterbox, Minimax
  • Support local video generation: FramePack integration and WAN 2.2.
  • 4K support, import any video, image or image sequences
  • Automatic trimming based on audio volume. Remove silent parts from video fast
  • Frame interpolation: increase video framerate
  • Image & Video upscaling
  • Project Start Wizard to get you started easily!
  • Easy and fast lyric import, lyric syncing made easy
    • Import lrc, vtt, srt and .tsv files, get your text directly to timeline
  • 91 crossfades / transitions
  • Drag & drop media directly to timeline
    • No need to meddle with “media library” or stuff like that. Just Drag & Drop media items from your folder directly to the timeline
  • Media Library support: Store your genAi materials for cross-project use. Filter items by name, tags, type etc
  • Add texts to videos, be it music video, visualizer, or just subtitles to existing video
    • Also support 3D text
  • Export lyrics from audio with local Whisper-integration and with ElevenLabs API integration
    • Can also separate vocals from background, keep both stems, create karaoke videos!
  • Color transfer / matching: make images / videos look more consistent
  • Storyboard mode: view your images in grid. Create a storyboard for your video before transforming images to video
  • Emphasizing ease of usage and fast manipulation and editing
  • Lot of effects. Can be set to project wide, track wide or just for single item
    • Transition & animations: animate almost any value of text lines, images and videos
    • Add audio volume modulation to effect values
  • Multi-track and timeline, audio, video, lyrics and AI content tracks supported. Keep your prompts organized!
  • Fast AI video creation by using lyrics directly to generate still images
  • LLM (Large Language Model) integrated. Convert your lyrics to descriptive prompts for images and video. Export then directly to your favorite plugin
    • Curated list of models to download
    • Mistral AI integration
  • Presets for plugins, primitives, effects
  • Video manipulation: color / chroma key removal & masking
    • Also support background removal with RemBg, with images & videos
  • Clipping for any items and tracks
  • Image cropping, also in bulk in image track
  • Video clipping / trimming + downscaling: for video-to-video purposes especially.
    • Clip video automatically based on audio volume OR extracted text
  • Export any resolution videos
    • Multihreaded off-screen video export rendering (except when using shaders!)
  • Multi-monitor support (detachable render view)
  • From musician to musicians!!! Developed to be easy and fast, with a mindset of ‘DAW’
  • No monthly fees! Pay once, keep forever (updates include bug fixes and content updates. New bigger features might require in app purchases or such, if any. 3rd party generative AI services usually require purchase of credits for their service)
  • Split video and audio, loop video, alternate the speed
  • Fragment Shader support. Add shaders to literally everything. Converter from GLSL to SKSL (Skiashard shading language) provided
  • Object detection and motions tracking for videos. Attach any item to video objects
  • Project archive to zip for easier sharing
  • Project archive, share and download with DropBox or Google drive! Easily share your project to your band mates, collaborators of clients!
  • Project import, for re-using materials (like intro / outro of the video, credits etc)
  • Copy media items under one folder for easier project sharing
  • Copy-paste text and files from your computer to timeline
  • Project rendering markers
  • Word-by-word offsetting (render one word at time from longer sentence)
  • Letter-by-letter transition
  • Karaoke mode
  • Edit multiple items at once
  • Copy multiple items / move them between tracks etc, all basic functionalities that all the video editing softwares should have
  • Duplicate tracks
  • Export frame
  • Start & end markers for video export fine tuning
    • Also custom markers supported
  • Gradient colors & blend mode for fonts: create beautifully colored fonts and blend them to background
  • Text backgrounds
  • Automatic lyric lining for long lines that would go off screen
  • Automatic opacity cross-fade for overlapping items
  • Timer & countdown support in texts
  • Split text items easily, either with default settings or prompt on each split
  • Transparent export rendering (optional, to png frames)
  • Tempo snap mode
  • Batch processing of items

Download installer and try for free

Trial Mode

Trial & demo mode is accessible from both stores. In Microsoft Store, you can see the trial button in the windows store. On their website, click the price button to open the store and activate trial. On steam, there’s small “Demo” button on right side of screen.
Trial restrictions
Amount of tracks: 5
Timeline length: 3 min
Frame rate: 30fps
Resolutions: Max 1280px
Watermark: Bottom right

LITE version

LITE-version is free in Microsoft Store. In addition to trial-mode restrictions, free version does not include local generative AI. 3rd party plugins is limited to default set. Audio-to-text extraction limited to API service(s). Video & image background removals (including green screen removal), color transfer, detachable render view or story mode are not available in LITE edition. LITE version is your perfect FREE video editing tool to start learning AI and video editing with. Audio and video recording is limited to 20 seconds.

You can enhance you LITE-version with various monthly based subscriptions. You can increase the limits described above with those. More info in the app

Multiple tracks enabled, edit AI content easily, fine tune your item values and animate them