LTX Desktop is an open-source, AI-powered video production suite currently in beta that runs entirely on your machine. It combines a full non-linear editor with on-device AI generation including text-to-video, image-to-video, audio-to-video, retake, image generation, and timeline import from professional NLEs. Everything runs locally, powered by the LTX-2.3 engine, with no internet connection required after installation.

The product offers comprehensive AI generation capabilities including text-to-video and image-to-video generation, still image generation via Z-Image Turbo, audio-to-video conversion, and retake functionality to regenerate specific portions of an input video. The full non-linear editor provides professional editing tools with trim tools (slip, slide, roll, and ripple), built-in transitions, and primary color correction tools. AI-native editing features include generating multiple takes per clip directly in the timeline, context-aware gap fill, and retake functionality for regenerating specific sections without leaving the timeline.

LTX Desktop operates entirely locally on your hardware with no cloud dependency, running on the LTX-2.3 multimodal engine. The application supports interoperability with professional NLEs through XML timeline import/export for Premiere Pro, DaVinci Resolve, and Final Cut Pro. It includes integrated text and subtitle workflow with text overlays, built-in subtitle editor, and SRT import/export capabilities.

The benefits include complete data privacy with footage, prompts, and outputs staying on your machine, zero usage fees after initial setup, and the ability to run offline after model downloads. Use cases include professional video editing workflows, AI-powered video generation, and content creation with privacy-focused requirements.

Target users include video editors, content creators, and developers who value privacy and operational control. The product supports both local deployment and API access, with system requirements including Windows 10/11 (64-bit) with NVIDIA GPU (32GB+ VRAM recommended) or macOS 13+ on Apple Silicon (M1 or later).