tufo830 / virtual_human_streamLinks
The "virtual_human_stream" project is a real-time digital human system supporting audio-video dialogue. It integrates models like ernerf, musetalk, and wav2lip for voice cloning, video stitching, and streaming via RTMP/WebRTC. It’s optimized for high performance and easy customization, with support for ChatGPT dialogue integration.
☆18Updated last year
Alternatives and similar repositories for virtual_human_stream
Users that are interested in virtual_human_stream are comparing it to the libraries listed below
Sorting:
- python库,实现推送实时rtmp 音视频流☆136Updated last year
- wav2lip384生成器网格权重——来自不蠢不蠢☆145Updated 10 months ago
- 优化wav2lip的执行步骤,将头脸分离、嘴型替换、回补背景三个步骤分离,添加gfpgan强化面部功能,实现提前解帧,流式循环处理,对接obs☆81Updated last year
- ☆242Updated 2 years ago
- Realtime Video and Audio Streaming with WebRTC and Gradio☆76Updated 7 months ago
- A docker free offline version for HeyGem; Python and Linux is all you need!☆417Updated 3 weeks ago
- ☆82Updated 6 months ago
- Simple python webrtc streaming demo☆71Updated 4 years ago
- Real time streaming talking head☆480Updated last year
- Just a suturing monster project.☆42Updated 2 years ago
- ☆38Updated 2 years ago
- ☆42Updated 2 years ago
- ☆416Updated 7 months ago
- 主要写er-nerf从零到一所有部署过程☆43Updated last year
- 使用vllm加速cosyvoice2的推理☆478Updated 9 months ago
- 在DH_live项目基础上修改,添加webui界面☆73Updated 9 months ago
- ☆379Updated last year
- 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☆175Updated last year
- 一个模块化,全过程可离线,低占用率的对话机器人/智能音箱☆131Updated 2 weeks ago
- ☆43Updated 6 months ago
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆47Updated last year
- Added vLLM support to IndexTTS for faster inference.☆1,039Updated 3 months ago
- 实时互动的GPT数字人技术笔记,不是数字人开源项目☆522Updated 7 months ago
- wav2lip训练数据预处理综合工具☆40Updated 2 years ago
- ☆68Updated 2 weeks ago
- The fastest digital human algorithm, now on your desktop.☆568Updated 4 months ago
- ☆75Updated last year
- 通过此代码可以免训练模型并通过轻量级服务器定制数字人形象☆106Updated last year
- 基于MuseTalk的数字人代码。☆35Updated last year
- ☆49Updated 2 years ago