HumanAIGC-Engineering / gradio-webrtcLinks
Realtime Video and Audio Streaming with WebRTC and Gradio
☆72Updated 3 months ago
Alternatives and similar repositories for gradio-webrtc
Users that are interested in gradio-webrtc are comparing it to the libraries listed below
Sorting:
- ☆372Updated 3 months ago
- Generate ARKit expression from audio in realtime☆150Updated 3 weeks ago
- JoyHallo: Digital human model for Mandarin☆509Updated 3 weeks ago
- [SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head☆803Updated last month
- 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☆79Updated 10 months ago
- EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation☆558Updated last month
- python库,实现推送实时rtmp音视频流☆133Updated last year
- talking-face video editing☆386Updated 7 months ago
- project page for ChatAnyone☆114Updated 6 months ago
- The fastest digital human algorithm, now on your desktop.☆552Updated 2 weeks ago
- ☆78Updated 2 months ago
- wav2lip384生成器网格权重——来自不蠢不蠢☆132Updated 7 months ago
- ☆43Updated 2 months ago
- DICE-Talk is a diffusion-based emotional talking head generation method that can generate vivid and diverse emotions for speaking portrai…☆263Updated 2 months ago
- A 2D customized lip-sync model for high-fidelity real-time driving.☆95Updated 3 months ago
- Real time streaming talking head☆483Updated last year
- 开源的LstmSync数字人泛化模型,只做最好的泛化模型!☆110Updated last week
- [NeurIPS 2025] OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication☆382Updated last month
- A docker free offline version for HeyGem; Python and Linux is all you need!☆347Updated 2 months ago
- ☆238Updated last year
- ☆49Updated last year
- ☆42Updated 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
- 基于MuseTalk的数字人代码。☆31Updated 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☆105Updated last year
- [ECCV'24] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting☆357Updated 7 months ago
- MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes; NeurIPS 2024; Official code☆782Updated last year
- Long-form streaming TTS system for multi-speaker dialogue generation☆795Updated last week
- PersonaTalk is a Node.js and Express.js-based API that enables users to interact with various digital personas using OpenAI's GPT model. …☆27Updated last month
- Official implementation of the paper "GUAVA: Generalizable Upper Body 3D Gaussian Avatar" [ICCV 2025]☆155Updated last week