diff --git a/demos/transformer/src/main/java/androidx/media3/demo/transformer/TransformerActivity.java b/demos/transformer/src/main/java/androidx/media3/demo/transformer/TransformerActivity.java
index de46144abb..d7e5d92e45 100644
--- a/demos/transformer/src/main/java/androidx/media3/demo/transformer/TransformerActivity.java
+++ b/demos/transformer/src/main/java/androidx/media3/demo/transformer/TransformerActivity.java
@@ -690,6 +690,7 @@ public final class TransformerActivity extends AppCompatActivity {
     ExoPlayer outputPlayer = new ExoPlayer.Builder(/* context= */ this).build();
     outputPlayerView.setPlayer(outputPlayer);
     outputPlayerView.setControllerAutoShow(false);
+    outputPlayerView.setOnClickListener(this::onClickingPlayerView);
     outputPlayer.setMediaItem(outputMediaItem);
     outputPlayer.prepare();
     this.outputPlayer = outputPlayer;
@@ -711,12 +712,13 @@ public final class TransformerActivity extends AppCompatActivity {
     } else {
       inputPlayerView.setVisibility(View.VISIBLE);
       inputImageView.setVisibility(View.GONE);
-      inputTextView.setText(getString(R.string.input_video));
+      inputTextView.setText(getString(R.string.input_video_no_sound));
 
       ExoPlayer inputPlayer = new ExoPlayer.Builder(/* context= */ this).build();
       inputPlayerView.setPlayer(inputPlayer);
       inputPlayerView.setControllerAutoShow(false);
       inputPlayer.setMediaItem(inputMediaItem);
+      inputPlayerView.setOnClickListener(this::onClickingPlayerView);
       inputPlayer.prepare();
       this.inputPlayer = inputPlayer;
       inputPlayer.setVolume(0f);
@@ -728,6 +730,20 @@ public final class TransformerActivity extends AppCompatActivity {
     debugTextViewHelper.start();
   }
 
+  private void onClickingPlayerView(View view) {
+    if (view == inputPlayerView) {
+      checkNotNull(inputPlayer).setVolume(1f);
+      checkNotNull(inputTextView).setText(R.string.input_video_playing_sound);
+      checkNotNull(outputPlayer).setVolume(0f);
+      checkNotNull(outputVideoTextView).setText(R.string.output_video_no_sound);
+    } else {
+      checkNotNull(inputPlayer).setVolume(0f);
+      checkNotNull(inputTextView).setText(getString(R.string.input_video_no_sound));
+      checkNotNull(outputPlayer).setVolume(1f);
+      checkNotNull(outputVideoTextView).setText(R.string.output_video_playing_sound);
+    }
+  }
+
   private void releasePlayer() {
     if (debugTextViewHelper != null) {
       debugTextViewHelper.stop();
diff --git a/demos/transformer/src/main/res/layout/transformer_activity.xml b/demos/transformer/src/main/res/layout/transformer_activity.xml
index c2585ebe8b..7304ead3ea 100644
--- a/demos/transformer/src/main/res/layout/transformer_activity.xml
+++ b/demos/transformer/src/main/res/layout/transformer_activity.xml
@@ -74,7 +74,7 @@
         android:layout_height="wrap_content"
         android:layout_marginBottom="8dp"
         android:padding="8dp"
-        android:text="@string/input_video" />
+        android:text="@string/input_video_no_sound" />
 
     <FrameLayout
       android:layout_width="match_parent"
@@ -118,7 +118,7 @@
         android:layout_width="match_parent"
         android:layout_height="wrap_content"
         android:layout_margin="8dp"
-        android:text="@string/output_video" />
+        android:text="@string/output_video_playing_sound" />
 
       <TextView
         android:id="@+id/debug_text_view"
diff --git a/demos/transformer/src/main/res/values/strings.xml b/demos/transformer/src/main/res/values/strings.xml
index 88da866994..aa021a9069 100644
--- a/demos/transformer/src/main/res/values/strings.xml
+++ b/demos/transformer/src/main/res/values/strings.xml
@@ -63,8 +63,10 @@
   <string name="saturation_adjustment">Saturation adjustment</string>
   <string name="lightness_adjustment">Lightness adjustment</string>
   <string name="input_image">Input image:</string>
-  <string name="input_video">Input video:</string>
-  <string name="output_video">Output video:</string>
+  <string name="input_video_no_sound">Input video (tap to play sound):</string>
+  <string name="input_video_playing_sound">Input video (sound playing):</string>
+  <string name="output_video_no_sound">Output video (tap to play sound):</string>
+  <string name="output_video_playing_sound">Output video (sound playing):</string>
   <string name="permission_denied">Permission Denied</string>
   <string name="hide_input_video">Hide input video</string>
   <string name="show_input_video">Show input video</string>