ZHANGYUXUAN-zR commited on
Commit
1447f2d
·
verified ·
1 Parent(s): 929bf86

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -3
README.md CHANGED
@@ -1,3 +1,39 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ - zh
6
+ base_model:
7
+ - Wan-AI/Wan2.2-S2V-14B
8
+ pipeline_tag: any-to-any
9
+ ---
10
+
11
+ # RealVideo
12
+
13
+ RealVideo is a WebSocket-based video calling system that supports text input. It leverages **GLM-4.5-AirX** and
14
+ **GLM-TTS** models to generate audio responses and utilizes autoregressive diffusion to generate corresponding video frames. The
15
+ system features a modular design with full functionality and a clean code structure.
16
+ Visit [blog](https://z.ai/blog/realvideo) here!
17
+
18
+ ## Features
19
+
20
+ - **Text Input**: Supports text message input.
21
+ - **AI Voice Response**: Integrates GLM-4.5-AirX and GLM-TTS models to generate voice responses.
22
+ - **Lip Sync**: Generates real-time conversational video based on any input image and audio.
23
+ - **Real-time Communication**: WebSocket-based real-time bidirectional communication.
24
+
25
+ ## Quick Start
26
+
27
+ you can check in our [GitHub](https://github.com/zai-org/RealVideo).
28
+
29
+ ## Technical Highlights
30
+
31
+ - **Model Integration**: Allows for convenient and quick voice cloning, taking text input to generate audio output.
32
+ - **Modular Design**: Clear code structure, easy to maintain and extend.
33
+ - **Real-time Performance**: Optimized audio processing and real-time video generation algorithms.
34
+
35
+ ## Acknowledgements
36
+
37
+ This project utilizes the following open-source libraries:
38
+
39
+ - [self forcing](https://github.com/guandeh17/Self-Forcing)