diff --git a/README.md b/README.md
index 47c8a0aa..d5249317 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,10 @@
 
 This is the inference code of [GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS) that can be developer-friendly.
 
+## Usage Example
+
+Check out the [example](example.ipynb) notebook for a quick start. Or open it in [Colab](https://colab.research.google.com/github/BeautyyuYanli/GPT-SoVITS-Infer/blob/main/example.ipynb)
+
 ## Prepare the environment
 
 As we all know, the dependencies of an AI project are always a mess. Here is how I prepare the environment for this project, by conda:
@@ -22,6 +26,8 @@ pip install GPT-SoVITS
 
 I do not add the packages related to torch to the dependencies of GPT-SoVITS-Infer. Check if the environment is ready if things go wrong.
 
-## Usage Example
+# Advanced Usage
 
-Check out the [example](example.ipynb) notebook for a quick start.
\ No newline at end of file
+- `GPTSoVITSInference.load_sovits` and `GPTSoVITSInference.load_gpt`: You can load your own fine-tuned model by the methods.
+- `GPTSoVITSInference.set_prompt_audio`: Set the prompt audio for the inference.
+- `GPTSoVITSInference.get_tts_wav_stream`: Return a generator that yields the audio pieces of the generated audio. It will create a background thread to generate the audio, so you can get the audio pieces while the audio is still being generated.
\ No newline at end of file