Self-hostable software: AI Media Generation (14)

ComfyUI is a modular node-based AI engine for creating images, video, 3D, audio, and other content with fine-grained control over models and parameters.

LocalAI is an open-source AI engine for running LLMs, vision, voice, image, and video models locally on a wide range of hardware.

A desktop app for running local LLMs with chat, vision, tool-calling, training, image generation, and an API.

LibreChat is a self-hosted AI chat platform that unifies major AI providers in a ChatGPT-like interface.

Open Notebook is a private, self-hosted, multi-model alternative to Google NotebookLM for organizing content, chatting with it, and generating podcasts.

SillyTavern is a locally installed interface for interacting with text generation LLMs, image generation engines, and TTS voice models.

KoboldCpp is a self-contained AI text-generation runner for GGML and GGUF models, with bundled UI, multiple inference modes, and broad support for image, audio, video, and vision tasks.

Big-AGI is a multi-model AI workspace for experts, focused on chat, model comparison, and local-first self-hosting.

GenCAD is a research project for image-conditioned CAD generation using transformer-based contrastive representations and diffusion priors.

SnapOtter is a self-hosted file-processing suite for converting, compressing, OCRing, transcribing, and editing media and documents through a UI, REST API, and pipelines.

FableCut is a browser-based non-linear video editor that can be driven by humans or AI agents through a JSON project file, MCP, or REST API.

OpenReader is an open source, self-host-friendly text-to-speech document reader for EPUB, PDF, TXT, MD, and DOCX with synchronized read-along playback.