diff --git a/README.md b/README.md
index 00a43f0..76f858d 100644
--- a/README.md
+++ b/README.md
@@ -33,8 +33,8 @@ Check out our other plugins:
 ## Download
 Check out the [latest releases](https://github.com/occ-ai/obs-cleanstream/releases) for downloads and install instructions.
 
-## Code Walkthrough
-This video walkthrough (YouTube) will explain various parts of the code of you're looking to learn from what I've discovered.
+## Method
+This video walkthrough (YouTube) will explain various parts of the code if you're looking to learn from what I've discovered.
 
 <div align="center">
     <a href="https://youtu.be/HdSI3sUKwsY" target="_blank">
@@ -42,6 +42,14 @@ This video walkthrough (YouTube) will explain various parts of the code of you'r
     </a>
 </div>
 
+### Audio processing
+
+The filter is running Whisper in real-time to detect words in small chunks of the incoming audio. For each chunck it produces a decision which then determines if the audio rendering will play the original audio or e.g. a beep or silence. The processing happens in a separate thread and therefore there's a built-in lag/delay mechanism to make sure the audio decision (play, beep, silence) is in-sync with the actual audio playback based on the timestamp. The built-in delay is adaptive since some systems (e.g. with CUDA) can make faster decisions.
+
+Here is an illustration of the process:
+
+![alt text](docs/image.png)
+
 ## Requirements
 - OBS version 30+ for plugin versions 0.0.4+
 - OBS version 29 for plugin versions 0.0.2+
@@ -118,3 +126,6 @@ To build with cuda add `CPU_OR_CUDA` as an environment variable (with `cpu`, `12
 > $env:CPU_OR_CUDA="12.2.0"
 > .github/scripts/Build-Windows.ps1 -Configuration Release
 ```
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=occ-ai/obs-cleanstream&type=Date)](https://star-history.com/#occ-ai/obs-cleanstream&Date)
diff --git a/docs/image.png b/docs/image.png
new file mode 100644
index 0000000..b1a1926
Binary files /dev/null and b/docs/image.png differ