diff --git a/README.md b/README.md
index e48b2a767695b2462967dbc6fe8c5047573780eb..d19003cff244152d900e652fdcc55a2d4d156cde 100644
--- a/README.md
+++ b/README.md
@@ -40,7 +40,7 @@ You will need the following whether you plan to use the toolbox only or to retra
 
 Run `pip install -r requirements.txt` to install the necessary packages. Additionally you will need [PyTorch](https://pytorch.org/get-started/locally/) (>=1.0.1).
 
-A GPU is mandatory, but you don't necessarily need a high tier GPU if you only want to use the toolbox.
+If you have a GPU, run `pip install -r requirements_gpu.txt` to enable GPU support. A GPU is recommended, but it is not required to use the toolbox.
 
 ### Pretrained models
 Download the latest [here](https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Pretrained-models).
diff --git a/requirements.txt b/requirements.txt
index e109ac5b0cf1068d64b6eadf27162967607b9e56..e513934f31f5d495199cccf78a0c781800fc17fb 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,8 +1,4 @@
-# each portion of tensorflow is needed
-# core package is for RNN, cpu and gpu are for specific system speed-ups
 tensorflow==1.15
-tensorflow-cpu==1.15
-tensorflow-gpu==1.15
 umap-learn
 visdom
 librosa>=0.5.1
diff --git a/requirements_gpu.txt b/requirements_gpu.txt
new file mode 100644
index 0000000000000000000000000000000000000000..ede24db20c5e30bbbf544e7c6d28f84fcda5a8cd
--- /dev/null
+++ b/requirements_gpu.txt
@@ -0,0 +1,5 @@
+# This is a list of recommended packages that also enables GPU support.
+# You will also need the packages listed in requirements.txt
+
+tensorflow-gpu==1.15   # Enables GPU support for synthesizer
+webrtcvad              # Better noise reduction when processing audio files