diff --git a/README.md b/README.md
index cba895c5..2c039dde 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@ pip install deepspeech-gpu
 deepspeech output_model.pb my_audio_file.wav alphabet.txt
 ```
 
-See the output of `deepspeech -h` for more information on the use of `deepspeech`.
+See the output of `deepspeech -h` for more information on the use of `deepspeech`. (If you experience problems running `deepspeech`, please check [required runtime dependencies](native_client/README.md#required-dependencies)).
 
 **Table of Contents**
 
diff --git a/native_client/README.md b/native_client/README.md
index c0c1c194..a6a488fe 100644
--- a/native_client/README.md
+++ b/native_client/README.md
@@ -16,6 +16,16 @@ If you want the CUDA capable version of the binaries, use `--arch gpu`. Note tha
 
 If you're looking to train a model, you now have a `libctc_decoder_with_kenlm.so` file that you can pass to the `--decoder_library_path` parameter of `DeepSpeech.py`.
 
+## Required Dependencies
+
+Running inference might require some runtime dependencies to be already installed on your system. Those should be the same, whatever the bindings you are using:
+* libsox2
+* libstdc++6
+* libgomp1
+* libpthread
+
+Please refer to your system's documentation on how to install those dependencies.
+
 ## Installing the language bindings
 
 For the Python bindings, you can use `pip`: