nxneo / LatentsyncRealtimeLinks
This project provides a production-ready, real-time inference server for LatentSync, enabling high-quality, low-latency 2D digital human live streaming. It features a robust multi-process architecture, seamless idle/formal stream switching with smooth crossfade transitions, and is optimized for real-world deployment scenarios.
☆20Updated 3 months ago
Alternatives and similar repositories for LatentsyncRealtime
Users that are interested in LatentsyncRealtime are comparing it to the libraries listed below
Sorting:
- 基于通义千问 Qwen2.5-Omni 的实时语音对话系统,使用在线API服务,支持实时语音交互、动态语音活动检测和流式音频处理。A real-time voice conversation system based on Qwen2.5-Omni Online-API, …☆81Updated 6 months ago
- Just a suturing monster project.☆42Updated 2 years ago
- 开源的LstmSync数字人泛化模型,只做最好的泛化模型!☆129Updated last week
- project page for ChatAnyone☆115Updated 8 months ago
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆172Updated 9 months ago
- 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
- ☆42Updated last year
- 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☆80Updated 11 months ago
- ☆79Updated 4 months ago
- FastAPI Server Implementation for Bilibili Index TTS☆26Updated 7 months ago
- 基于MuseTalk的数字人代码。☆31Updated last year
- 私有化自动数字人排队训练、短视频排队生成的微信小程序、web运营后台管理系统一键部署,基于单人训练的音频驱动唇形,比wav2lip、deepfacelab、liveportrait、musetalk等等唇形方案更好,直接可以商业化,支持中日英韩多种语音复刻☆52Updated 7 months ago
- python库,实现推送实时rtmp音视频流☆135Updated last year
- 基于中文文本情绪分析自动切换参考音频的 GPT-SoVITS 推理 Demo☆106Updated last year
- This is a project about talking faces. We use 576X576 sized facial images for training, which can generate 2k, 4k, 6k, and 8k digital hum…☆54Updated last year
- ☆31Updated 4 months ago
- ☆391Updated 5 months ago
- ChatTTS HTTP API☆54Updated last year
- ☆28Updated 2 years ago
- 在DH_live项目基础上修改,添加webui界面☆72Updated 7 months ago
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆145Updated 5 months ago
- A docker free offline version for HeyGem; Python and Linux is all you need!☆379Updated 4 months ago
- WebUI build on SambertHifigan-TTS☆11Updated 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☆173Updated last year
- wav2lip384生成器网格权重——来自不蠢不蠢☆139Updated 8 months ago
- 一个用于CosyVoice的api接口项目☆321Updated 3 months ago
- ☆75Updated last year
- This is a multi-character, ultra-personalized StoryTeller. It includes: 1) efficiently and accurately build multi-character voice library…☆57Updated 10 months ago
- 用于SenseVoice的api项目,输出带时间戳字幕☆43Updated last year
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆25Updated last year