Awesome GitHub RepositoriesConversational Avatar Animators

Airi is an interactive digital companion engine designed to bridge large language models with local animation rendering. It functions as a middleware platform that synchronizes conversational text streams with skeletal and facial movements to drive virtual avatars in real time. The framework distinguishes itself by integrating desktop context awareness, allowing characters to maintain situational awareness of a user's screen activity across both desktop and web environments. It utilizes a hybrid execution model that splits computational workloads between cloud-based language processing and lo

LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with users through voice, video, and text. It provides a centralized, event-driven architecture to manage the entire lifecycle of automated participants, from initialization and session state management to graceful shutdown. By utilizing a selective forwarding unit, the platform efficiently routes media streams between participants and agents, ensuring low-latency communication and secure, token-based authentication for all connections. The platform distinguishes itself through it

Duix-Avatar is an AI digital human toolkit used to create, clone, and animate realistic virtual personas. It functions as a digital persona cloning tool and a text-to-speech animation API that converts written text or audio into synthetic voice and facial motion markers. The framework provides an offline video generation engine that renders digital human animations and lip-synced videos on local hardware. It includes a specialized lip sync engine to synchronize mouth movements with audio waveforms and a pipeline for extracting facial and vocal features from source media to create synthetic re

Fay is an artificial intelligence framework designed to build autonomous agents capable of managing both interactive virtual personas and automated financial trading operations. The platform integrates large language models with specialized modules to coordinate complex tasks, enabling the synchronization of speech and movement for digital avatars alongside the execution of market-based financial strategies. The system distinguishes itself through an event-driven orchestration model that routes signals between perception, decision-making, and action-execution components. It utilizes a modular

Ten Framework is a multimodal large language model agent framework designed for building low-latency conversational agents. It integrates voice, text, and visual inputs in real time to facilitate human interaction. The project includes a real-time speech processing pipeline for streaming transcription, voice activity detection, and speaker diarization. It also features an avatar synchronization engine that coordinates character lip animations and visual outputs with synthesized speech. The framework covers edge AI deployment through containerized packaging and direct integration with embedde

elevator.js is a lightweight JavaScript library that adds a playful, elevator-themed scroll-to-top button to a webpage. When clicked, it smoothly animates the page back to the top while playing a looping elevator music track in the background, masking the transition and adding a whimsical touch to the user experience. The library goes beyond a simple scroll-to-top button by offering configurable scroll duration, the ability to scroll to any specified DOM element with optional vertical padding, and callback hooks that fire user-defined functions at the start and end of the animation. This allo

hexo-helper-live2d is a plugin for adding interactive 2D animated characters to static websites generated with the Hexo framework. It functions as a configuration-driven system that embeds and manages character assets within static pages via build-time script automation. The project provides a manager for loading and positioning character assets from local directories or remote URLs. It uses an HTML canvas to render animated models that respond to mouse and touch movements. The system covers character visual configuration, including controls for scale, screen position, opacity, and mobile vi

WebGAL is a web-native development environment designed for the creation and publication of interactive narrative games. It provides a browser-based platform that enables users to build visual novels featuring branching dialogue and multimedia assets without requiring manual coding. The platform distinguishes itself through a visual editor that utilizes node-based logic definition to manage narrative flow and scene transitions. It includes specialized tooling for the configuration and integration of animated character models, allowing for the direct implementation of interactive character seq

VirtualWife is a framework for creating interactive 3D digital companions powered by large language models. It integrates a browser-based rendering engine that synchronizes 3D model animations and facial expressions with AI-generated dialogue in real time, supported by a voice interaction system that converts text into synthesized speech. The system features a persona manager for defining role-play prompts, visual identities, and long-term conversational memory. It also includes a bridge for live streaming integration, allowing an AI avatar to interact with live audiences by monitoring commen