googleapis
diff --git a/‎google/cloud/texttospeech/v1/cloud_tts.proto‎
Lines changed: 6 additions & 0 deletions b/‎google/cloud/texttospeech/v1/cloud_tts.proto‎
Lines changed: 6 additions & 0 deletions
@@ -281,6 +281,12 @@ message SynthesisInput {
     MultiSpeakerMarkup multi_speaker_markup = 4;
   }
 
+  // This system instruction is supported only for controllable/promptable voice
+  // models. If this system instruction is used, we pass the unedited text to
+  // Gemini-TTS. Otherwise, a default system instruction is used. AI Studio
+  // calls this system instruction, Style Instructions.
+  optional string prompt = 6;
+
   // Optional. The pronunciation customizations are applied to the input. If
   // this is set, the input is synthesized using the given pronunciation
   // customizations.