diff --git a/docs/img/MultiNet_model.png b/docs/img/MultiNet_model.png
new file mode 100644
index 0000000..939bc51
Binary files /dev/null and b/docs/img/MultiNet_model.png differ
diff --git a/docs/img/WakeNet_model.png b/docs/img/WakeNet_model.png
new file mode 100644
index 0000000..2ddcec6
Binary files /dev/null and b/docs/img/WakeNet_model.png differ
diff --git a/docs/speech_command_recognition/README.md b/docs/speech_command_recognition/README.md
index 0780c53..41abd97 100644
--- a/docs/speech_command_recognition/README.md
+++ b/docs/speech_command_recognition/README.md
@@ -6,6 +6,10 @@ MultiNet is a lightweight model specially designed based on [CRNN](https://arxiv
 
 MultiNet uses the **MFCC features** of an audio clip as input, and the **phonemes** (Chinese or English) as output. By comparing the output phonemes, the relevant Chinese or English command is identified.
 
+The following table shows the model support of Espressif SoCs:
+
+![multinet_model](../img/MultiNet_model.png)
+
 ## Commands Recognition Process
 
 1. Add customized commands to the speech command queue.
diff --git a/docs/speech_command_recognition/README_cn.md b/docs/speech_command_recognition/README_cn.md
index 3d2c457..404ce72 100644
--- a/docs/speech_command_recognition/README_cn.md
+++ b/docs/speech_command_recognition/README_cn.md
@@ -6,6 +6,10 @@ MultiNet 是为了在 ESP32 上实现多命令词识别, 基于 [CRNN](https://a
 
 MultiNet 输入为音频经过 **MFCC** 处理后的特征值，输出为汉语/英语的“音素”分类。通过对输出音素进行组合，则可以对应到相应的汉字或单词。  
 
+以下表格展示在不同芯片上的模型支持：
+
+![multinet_model](../img/MultiNet_model.png)
+
 ## 命令词识别流程
 
 1. 添自定义命令词
diff --git a/docs/wake_word_engine/README.md b/docs/wake_word_engine/README.md
index 9a5ff7d..5ee7d50 100644
--- a/docs/wake_word_engine/README.md
+++ b/docs/wake_word_engine/README.md
@@ -24,6 +24,9 @@ Please see the flow diagram of WakeNet below:
 - Keyword Triggering Method  
   For continuous audio stream, we calculate the average recognition results (M) for several frames and generate a smoothing prediction result, to improve the accuracy of keyword triggering. Only when the M value is larger than the set threshold, a triggering command is sent.  
 
+The following table shows the model support of Espressif SoCs:
+
+![wakent_model](../img/WakeNet_model.png)
 
 ## API Introduction
 
diff --git a/docs/wake_word_engine/README_cn.md b/docs/wake_word_engine/README_cn.md
index bdc9fe7..2742784 100644
--- a/docs/wake_word_engine/README_cn.md
+++ b/docs/wake_word_engine/README_cn.md
@@ -24,6 +24,9 @@ WakeNet的流程图如下：
 - keyword trigger method：  
   对连续的音频流，为准确判断关键词的触发，我们通过计算若干帧内识别结果的平均值M，来判断触发。当M大于大于指定阈值，发出触发的命令。
 
+以下表格展示在不同芯片上的模型支持：
+
+![wakent_model](../img/WakeNet_model.png)
 
 ## API introduction