Readme: Instructions for video demo

README.md

@@ -4,7 +4,7 @@ Multispeaker Text-To-Speech Synthesis](https://arxiv.org/pdf/1806.04558.pdf) (SV
 
 SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.
 
-**Video demonstration:**
+**Video demonstration (click the picture):**
 
 [![Toolbox demo](https://i.imgur.com/Ixy13b7.png)](https://www.youtube.com/watch?v=-O_hYhToKoA)