Quantized text-audio foundation model from Boson AI

开源的LstmSync数字人泛化模型，只做最好的泛化模型！

Bella is best

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline

This package loads the espeak-ng shared library so it will be available for other libraries.

Live2D Library for Python (C++ impl): Supports model loading, lip-sync, basic face rigging, and precise click test.

Taming Stable Diffusion for Lip Sync!

Quick Mflux on ComfyUI

An implementation of MeloTTS by onnxruntime

A passive recording project allows you to have complete control over your data. Automatically take screenshots of all your screens, index them, and save them locally.

gradio WebUI for AdvancedLivePortrait

洛曦 数字人视频播放器，带HTTP API，使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk，也可以用于播放本地视频

The fastest digital human algorithm, now on your desktop.

GOT-OCR的GUI版本，提供OCR、导出PDF、批处理等功能，但不提供训练功能

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Powerful Free DeepL API, No Token Required

[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

在DH_live项目基础上修改，添加webui界面

Next-Token Prediction is All You Need

桌面Live2D，提供自定义聊天接口，支持更换模型，自定义动作语音+文本

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Industry leading face manipulation platform

zero-shot voice conversion & singing voice conversion, with real-time support

An easy-to-use web framework. Supports both WSGI and ASGI modes. Gevent or asyncio, this is the question.

GPT-SoVITS-V2模型，合并了官方的一些PR，包含但不限于:参考音频自动填充，字幕同步，SillyTavern酒馆接入等功能

一个基于Flask实现的RWKV_Role_Playing项目的API。