OpenMOSS

An open-source, tool-augmented conversational language model from Fudan University

A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness

A curated collection of papers, explainers, and resources on World Action Models for embodied AI

A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and zero-shot voice cloning

A foundation model that generates synchronized video and audio in a single model

A unified multimodal language model based on discrete sequence modeling

An open-weight 11B model series for long-form and real-time video understanding

An open-source model for understanding speech, environmental sounds, and music through captioning, question answering, and reasoning

A large-scale benchmark for evaluating vision-language-action models, embodied agents, and vision-language models

An efficient framework for collaborative training of large language models

A unified framework for training, fine-tuning, and evaluating World Action Models

A real-time spoken dialogue system for direct speech-to-speech interaction

A 1.6B causal Transformer audio tokenizer with streaming, variable bitrates, and semantic alignment across speech, sound, and music

A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods

An open-source model for music captioning, lyrics transcription, structural analysis, and musical question answering

An embodied task agent that connects perception, action, verification, and learning in a continuous physical-world loop

[arXiv 26] Language-guided whole-body control for general humanoid robots

An 11B model for real-time video understanding with gated cross-attention and streaming inference

A post-training framework for diffusion language models with supervised fine-tuning and reinforcement learning

An end-to-end speech-to-speech language model that generates spoken responses without text guidance

Dataset and evaluation code for measuring hallucinations in Chinese large language models

A proactive robot manipulation model for multimodal physical environments

A unified audio-video variational autoencoder with cross-modal alignment for joint reconstruction and generation

Code and data for evaluating whether AI assistants know when they do not know the answer

A benchmark for testing whether coding agents can resolve engineering tasks in scientific software

A Chinese human-level benchmark for evaluating multimodal large language models

A full-duplex real-time interaction system with live audio and vision, continuous conversation, and background tool use.

A survey of long-context language models covering architecture, infrastructure, training, and evaluation

A local browser reading app powered by MOSS-TTS-Nano with in-browser ONNX inference

Methods and code for extending the context length of diffusion language models

Band-constrained Policy Optimization with probability-aware clipping for LLM reinforcement learning