Xipeng Qiu

Yitian Gong, Botian Jiang, et al., "MOSS-TTS Technical Report,", arxiv.org/abs/2603.18090

MOSS-Audio-Tokenizer A 1.6B parameter pure Transformer audio tokenizer trained end-to-end on 3M hours of audio. Scales gracefully across speech, sound, and music while enabling the first purely autoregressive TTS to surpass non-autoregressive systems.

More details are in our paper: interp.open-moss.com/posts/complete… Code and replacement layer weights will be open-sourced later. Still writing the docs and testing! github.com/OpenMOSS/Langu…

Yitian Gong, Kuangwei Chen, Zhaoye Fei, Xiaogui Yang, Ke Chen, Yang Wang, Kexin Huang, Mingshu Chen, Ruixiao Li, Qingyuan Cheng, Shimin Li, Xipeng Qiu, "MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models," arxiv.org/abs/2602.10934

WOW! New vid model - MOSS-Video-and-Audio: - native bimodal gen, IT2VA,T2VA; - 32B MoE for sync video & audio in one pass, - SOTA multilingual lip-sync + Sound FX; - 360p/720p, with code, weights & LoRA. Beyond words. Seriously cool. mosi.cn/models/mova

We took iconic screenshots from classic cinema and remake the scene using #MOVA. 🎬✨ github.com/OpenMOSS/MOVA Our focus was on seamless end-to-end audio & video generation. #AIVideo #OpenSource #ClassicMovies #GenAI

MOVA (MOSS Video and Audio), a foundation model designed to synthesizes video and audio simultaneously github.com/OpenMOSS/MOVA

Hot! We have a new strong voice model. MOSS-TTS - a production-ready flagship 8B TTS; - high-fidelity zero-shot voice cloning, stable long-form gen; - multilingual; - lossless reconstruction; fine-grained pronunciation control; - token-level duration control, - voice creator, sound effects. Outstanding quality. mosi.cn/models/moss-tts

🚀 The MOSS-TTS Family is here. From zero-shot cloning to real-time VoiceAgents, we have released our most powerful suite of audio models yet. The Lineup: MOSS-TTS Flagship: The industry's best zero-shot voice cloning. Features precise control over duration & Pinyin, capable of generating 1 hour of speech. MOSS-TTSD-v1.0: A new standard for dialogue generation. Comprehensive optimization for conversational scenes and small languages. Best-in-class performance in all evaluations. MOSS-VoiceGenerator: One-shot timbre generation. Create voices with a single sentence and complex instruction handling. MOSS-TTS-Realtime: Built for the next era of VoiceAgents. Synthesis starts in just 2 characters for instant response. MOSS-SoundEffect: Text-to-Audio sound effects to expand your creative toolkit. 🔥 Try it now: studio.mosi.cn/voice-synthesis 💻 Deploy (GitHub): github.com/OpenMOSS/MOSS-… 🔌 API Docs: studio.mosi.cn/docs/moss-tts Welcome to our demo. The era of 'childhood' for TTS is over. #MOSS #AI #TextToSpeech #TTS #OpenClaw #Agent #OpenMOSS #Opensource #VoiceAgent

Ever wanted to turn text into natural-sounding speech with just a few lines of code? Meet MOSS-TTSD-v1.0, a text-to-speech model that's making voice synthesis more accessible. It's a community favorite for its simplicity and quality.

Paper: huggingface.co/papers/2602.08… Models: huggingface.co/collections/Op… Project: mosi.cn/models/mova

MOVA: Towards Scalable and Synchronized Video–Audio Generation huggingface.co/papers/2602.08… github.com/OpenMOSS/MOVA

MOVA: Towards Scalable and Synchronized Video-Audio Generation huggingface.co/papers/2602.08…

🎥@Open_MOSS and #MOSI unveil MOVA—a fully open-source audio-visual model delivering film-grade lip sync and sound-image co-generation as a bold alternative to closed giants！🎬#VideoAI pandaily.com/open-moss-and-…

MOVA ends the silent era of open video: #SynchronizedGeneration with native #MultimodalAI delivers lip-synced video-audio in one pass. 12GB VRAM via MoE offloading? This #OpenSourceWave changes everything. banandre.com/blog/mova-brea…

We introduce MOVA, a foundation model designed to break the "silent era" of open-source video generation. Unlike cascaded pipelines that generate sound as an afterthought, MOVA synthesizes video and audio simultaneously for perfect alignment. github.com/OpenMOSS/MOVA

NEX is a project incubated by Shanghai Innovation Institute (nex.sii.edu.cn) , jointly with many entrepreneurial partners. The project is building a sustainable closed-loop open ecosystem that powers industry upgrades and truly ushers in the AI agency era.

Nex-N1, the SOTA open-source agentic foundation model Nex-AGI Homepage: nex-agi.com/en/ Github: github.com/nex-agi Hugging Face: huggingface.co/nex-agi

Welcome Nex-N1, a new series of agentic foundational models, to @huggingface - available in different sizes from 8B, 30B, 32B to 671B - strong in tool-use, web-search and real-world agentic workflow - some SFT dataset has been open sourced Technical report come up soon!

@Xianbao_QIAN @huggingface Use NEX to create a 3D game.