LTX-2 is a next-generation multimodal AI model for video created by Lightricks. It combines visual generation with synchronized audio, helping teams create new videos or rework existing footage quickly while maintaining studio-level output.
Multimodal video and audio generation
LTX-2 supports working with video and sound at the same time, aiming for accurate sync and natural results. It can be used for both original creation and improving or repurposing content for different formats and platforms.
Built for speed, quality, and cost control
According to the developers, LTX-2 ranks among the top three AI models globally and delivers studio-quality results at a significantly lower cost. This makes it relevant for teams that need to scale production without losing budget visibility.
For products and integrations
LTX-2 can serve as a foundation for integrating AI video capabilities into apps, services, and creative pipelines.
- Generate new videos with synced audio
- Enhance existing videos
- Repurpose content across platforms and formats
- Build custom AI video editors and generators via API and developer tools
