Starred repositories
An AI-powered interactive avatar engine using Live2D, LLM, ASR, TTS, and RVC. Ideal for VTubing, streaming, and virtual assistant applications.
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and …
Voice activity detector (VAD) for the browser with a simple API
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head
Real time interactive streaming digital human
ContextGem: Effortless LLM extraction from documents
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / Swift / Ultralytics…
基于树莓派和GPT实现的多功能语音家庭助手 A multifunctional voice home assistant based on Raspberry Pi and GPT
Future versions with model training module will be maintained through a forked version here: https://github.com/seasalt-ai/snowboy
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Auto Thinking Mode switch for Qwen3 in Open webui
Building a quick conversation-based search demo with Lepton AI.
The official Python SDK for the Aipolabs API
ACI.dev is the open source platform that connects your AI agents to 600+ tool integrations with multi-tenant auth, granular permissions, and access through direct function calling or a unified MCP …
Suna - Open Source Generalist AI Agent
Model Context Protocol Servers for Milvus
Mirror of https://github.com/longbowzz/svg2png_mcp