Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Voice activity detector (VAD) for the browser with a simple API

A Chrome extension for focus and productivity with Pomodoro Timer and website blocking | 专注效率提升的 Chrome 插件，集成番茄钟和网站屏蔽功能

Real-time voice assistant with multi-speaker recognition & tactical suggestions. Local AI processing for privacy-sensitive scenarios (debates/meetings/negotiations).

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

基于多模态大模型的智能搜索助手，通过AI技术实现小红书平台的智能化信息检索和知识整合|An intelligent search assistant based on multimodal large models, enabling smart information retrieval and knowledge integration on the Xiaohongshu platform.

Multilingual Voice Understanding Model

A fast multimodal LLM for real-time voice

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)

[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Multimodal Real-time Audio-Video Chatting Intelligent Assistant

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Python sample codes and textbook for robotics algorithms.

Code and dataset for photorealistic Codec Avatars driven from audio

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

基于Bert-VITS2做的表情、动画测试. Animation testing based on Bert-VITS2.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

vits2 backbone with multilingual-bert

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

The official implementation of the paper "Human Motion Diffusion as a Generative Prior"

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

An Open-Ended Embodied Agent with Large Language Models

ImageBind One Embedding Space to Bind Them All

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.