diff --git a/README.md b/README.md
index 06df542aa4cc70dbdec6b1864ce00c675f5d57a2..24140391d11d6de158d801949b59700046313b77 100644
--- a/README.md
+++ b/README.md
@@ -70,6 +70,8 @@ python s2s_pipeline.py --recv_host localhost --send_host localhost
 python listen_and_play.py --host localhost
 ```
 
+You can pass `--device mps` to run it locally on a Mac.
+
 ### Recommended usage
 
 Leverage Torch Compile for Whisper and Parler-TTS:
@@ -86,8 +88,6 @@ python s2s_pipeline.py \
 
 For the moment, modes capturing CUDA Graphs are not compatible with streaming Parler-TTS (`reduce-overhead`, `max-autotune`).
 
-
-
 ## Command-line Usage
 
 ### Model Parameters