MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenario…

OpenMOSS pure C++ pipeline based on GGML

Generates dynamic, interactive-textbook lessons on the fly based on user interests and immediate doubts. Maps the learning journey as a tree structure, allowing users to backtrack to the previous s…

A repository for agentic world building to roleplay in. A world seed template is used for the pipeline and the output is a Silly Tavern ready character cards, world info and system settings.

Linux software for the Stream Deck with support for original Elgato Stream Deck plugins

High-Quality Voice Cloning TTS for 600+ Languages

Open Source Speech Language Model

Fully automatic censorship removal for language models

Adventure Kid Wave Forms are a collection of sampled one cycle waveforms for use in synthesizers and samplers or similar sound generators.

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)

VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)

Noise supression using deep filtering

A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.

Scheduler for ComfyUI and an attempt at optimized scheduler for the Chroma architecture.

RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library

[AAAI 2025] Event-Enhanced Blurry Video Super-Resolution

[NeurIPS'25] One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & En…

Lets make video diffusion practical!

The official implementation of Self-Play Preference Optimization (SPPO)

OpenAI compatible TTS for Sesame CSM:1b & dia:1.6b - Voice Cloning from File/YT

A Conversational Speech Generation Model

Roland S1 "Tweak" synthesiser quick reference sheet

A cli app for experimenting with kokoro voice creating and mixing using the available voices to interpolate new ones