diff --git a/README.md b/README.md
index 4e50bf092b1cdbc460e53ce688795a7c63c7ad28..fcf5953aaf1b3c5f59eb0976d99f055a4f0a447a 100644
--- a/README.md
+++ b/README.md
@@ -109,19 +109,19 @@ Developers can have a try of our models with [PaddleSpeech Command Line](./paddl
 
 **Audio Classification**     
 ```shell
-paddlespeech cls --input ./test_audio.wav
+paddlespeech cls --input input.wav
 ```
 **Automatic Speech Recognition**
 ```shell
-paddlespeech asr --lang zh --sr 16000 --input ./input.wav
+paddlespeech asr --lang zh --input input_16k.wav
 ```
 **Speech Translation** (English to Chinese)
 ```shell
-paddlespeech st --input ./test_audio.wav
+paddlespeech st --input input_16k.wav
 ```
 **Text-to-Speech** 
 ```shell
-paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！"
+paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav
 ```
 
 If you want to try more functions like training and tuning, please see [Speech-to-Text Quick Start](./docs/source/asr/quick_start.md) and [Text-to-Speech Quick Start](./docs/source/tts/quick_start.md).