Open Source Video AI tools

opencut.app is an open-source, privacy-first video...

opencut.app is an open-source, privacy-first video editor in early beta that enables cross-platform timeline editing with dark theme and standard export formats. It prioritizes local, auditable workflows for creators and developers, supported by an active community and public roadmap.

Palmier is an AI video editor combining timeline-b...

Palmier is an AI video editor combining timeline-based editing, AI generation, and agent workflows to automate content creation, scene assembly, and multi-step media processing, with editable timelines, team collaboration, macOS support, and GitHub-compatible export.

OpenMontage is an open-source agentic video produc...

OpenMontage is an open-source agentic video production system that automates end-to-end workflows with modular pipelines, 50+ tools and 500+ agent skills for storyboarding, character animation, TTS, composition and reproducible rendering across configurable model and media providers.

LTX Desktop is an open-source AI video production ...

LTX Desktop is an open-source AI video production suite using the LTX-2.3 multimodal engine for local text-to-video, image-to-video and audio-to-video generation, combined with a non-linear editor, timeline tools, subtitle/XML interoperability and on-prem model management.

Magi-1 is an open-source autoregressive diffusion ...

Magi-1 is an open-source autoregressive diffusion model that converts images into high-quality videos, featuring advanced temporal modeling for smooth transitions and automatic infinite video extensions. The tool supports community collaboration with a transparent codebase and technical reports.

WAN2.1 by WANAI is a video generation model by Ali...

WAN2.1 by WANAI is a video generation model by Alibaba Cloud that transforms text inputs into high-quality, realistic videos with precise movements. It supports multiple languages, offers customizable outputs, and provides APIs for seamless integration into applications like education and creative projects.

VoiceCraft is an advanced tool for zero-shot speec...

VoiceCraft is an advanced tool for zero-shot speech editing and text-to-speech (TTS), adept at handling diverse data sources like audiobooks, internet videos, and podcasts. It achieves state-of-the-art performance, offering model weights, training guidance, and multiple inference methods.

Lumiere is an innovative AI tool that transforms ...

Lumiere is an innovative AI tool that transforms text or images into high-quality videos with stylish flair. It excels in generating motion and lifelike visual effects, redefining the video synthesis standard.

MotionAgent is an AI assistant that turns ideas in...

MotionAgent is an AI assistant that turns ideas into motion pictures using deep learning models, allowing users to generate videos from scripts, create movie stills, compose music, and customize styles easily. Suitable for bringing story ideas to life through AI video creation.

The Google-research/frame-interpol is a public API...

The Google-research/frame-interpol is a public API tool that allows users to run models to interpolate frames in large scenes of motion with state-of-the-art results, and is typically completed within 36 seconds using NVIDIA T4 GPU hardware.