Make utterance_id 64-bit.

bruvzg · bruvzg · commit 281c74550a8c · 2025-11-07T10:21:20.000+02:00
diff --git a/drivers/apple_embedded/display_server_apple_embedded.h b/drivers/apple_embedded/display_server_apple_embedded.h
@@ -142,7 +142,7 @@ class DisplayServerAppleEmbedded : public DisplayServer {
 	virtual bool tts_is_paused() const override;
 	virtual TypedArray<Dictionary> tts_get_voices() const override;
 
-	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int p_utterance_id = 0, bool p_interrupt = false) override;
+	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int64_t p_utterance_id = 0, bool p_interrupt = false) override;
 	virtual void tts_pause() override;
 	virtual void tts_resume() override;
 	virtual void tts_stop() override;
diff --git a/drivers/apple_embedded/display_server_apple_embedded.mm b/drivers/apple_embedded/display_server_apple_embedded.mm
@@ -413,7 +413,7 @@
 	return [tts getVoices];
 }
 
-void DisplayServerAppleEmbedded::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
+void DisplayServerAppleEmbedded::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {
 	if (unlikely(!tts)) {
 		initialize_tts();
 	}
diff --git a/drivers/apple_embedded/tts_apple_embedded.h b/drivers/apple_embedded/tts_apple_embedded.h
@@ -44,7 +44,7 @@
 
 @interface GDTTTS : NSObject <AVSpeechSynthesizerDelegate> {
 	bool speaking;
-	HashMap<id, int> ids;
+	HashMap<id, int64_t> ids;
 
 	AVSpeechSynthesizer *av_synth;
 	List<DisplayServer::TTSUtterance> queue;
@@ -55,6 +55,6 @@
 - (void)stopSpeaking;
 - (bool)isSpeaking;
 - (bool)isPaused;
-- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int)utterance_id interrupt:(bool)interrupt;
+- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int64_t)utterance_id interrupt:(bool)interrupt;
 - (Array)getVoices;
 @end
diff --git a/drivers/apple_embedded/tts_apple_embedded.mm b/drivers/apple_embedded/tts_apple_embedded.mm
@@ -87,10 +87,9 @@ - (void)update {
 
 		ids[new_utterance] = message.id;
 		[av_synth speakUtterance:new_utterance];
+		DisplayServer::get_singleton()->tts_post_utterance_event(DisplayServer::TTS_UTTERANCE_STARTED, message.id);
 
 		queue.pop_front();
-
-		DisplayServer::get_singleton()->tts_post_utterance_event(DisplayServer::TTS_UTTERANCE_STARTED, message.id);
 		speaking = true;
 	}
 }
@@ -120,7 +119,7 @@ - (bool)isPaused {
 	return [av_synth isPaused];
 }
 
-- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int)utterance_id interrupt:(bool)interrupt {
+- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int64_t)utterance_id interrupt:(bool)interrupt {
 	if (interrupt) {
 		[self stopSpeaking];
 	}
diff --git a/misc/extension_api_validation/4.5-stable.expected b/misc/extension_api_validation/4.5-stable.expected
@@ -99,3 +99,10 @@ Validate extension JSON: Error: Field 'builtin_classes/PackedVector3Array/method
 Validate extension JSON: Error: Field 'builtin_classes/PackedVector4Array/methods/duplicate': is_const changed value in new API, from false to true.
 
 Duplicate method made const. Compatibility methods registered.
+
+
+GH-112379
+---------
+Validate extension JSON: Error: Field 'classes/DisplayServer/methods/tts_speak/arguments/5': meta changed value in new API, from "int32" to "int64".
+
+`utterance_id` argument changed from `int32` to `int64`. No compatibility method needed.
diff --git a/platform/android/display_server_android.cpp b/platform/android/display_server_android.cpp
@@ -109,7 +109,7 @@ TypedArray<Dictionary> DisplayServerAndroid::tts_get_voices() const {
 	return TTS_Android::get_voices();
 }
 
-void DisplayServerAndroid::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
+void DisplayServerAndroid::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {
 	TTS_Android::speak(p_text, p_voice, p_volume, p_pitch, p_rate, p_utterance_id, p_interrupt);
 }
 
diff --git a/platform/android/display_server_android.h b/platform/android/display_server_android.h
@@ -110,7 +110,7 @@ class DisplayServerAndroid : public DisplayServer {
 	virtual bool tts_is_paused() const override;
 	virtual TypedArray<Dictionary> tts_get_voices() const override;
 
-	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int p_utterance_id = 0, bool p_interrupt = false) override;
+	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int64_t p_utterance_id = 0, bool p_interrupt = false) override;
 	virtual void tts_pause() override;
 	virtual void tts_resume() override;
 	virtual void tts_stop() override;
diff --git a/platform/android/java/lib/src/main/java/org/godotengine/godot/GodotLib.java b/platform/android/java/lib/src/main/java/org/godotengine/godot/GodotLib.java
@@ -105,7 +105,7 @@ public static native boolean initialize(
 	/**
 	 * TTS callback.
 	 */
-	public static native void ttsCallback(int event, int id, int pos);
+	public static native void ttsCallback(int event, long id, int pos);
 
 	/**
 	 * Forward touch events.
diff --git a/platform/android/java/lib/src/main/java/org/godotengine/godot/tts/GodotTTS.java b/platform/android/java/lib/src/main/java/org/godotengine/godot/tts/GodotTTS.java
@@ -119,7 +119,7 @@ private void updateTTS() {
 	@Override
 	public void onRangeStart(String utteranceId, int start, int end, int frame) {
 		synchronized (lock) {
-			if (lastUtterance != null && Integer.parseInt(utteranceId) == lastUtterance.id) {
+			if (lastUtterance != null && Long.parseLong(utteranceId) == lastUtterance.id) {
 				lastUtterance.offset = start;
 				GodotLib.ttsCallback(EVENT_BOUNDARY, lastUtterance.id, start + lastUtterance.start);
 			}
@@ -132,7 +132,7 @@ public void onRangeStart(String utteranceId, int start, int end, int frame) {
 	@Override
 	public void onStop(String utteranceId, boolean interrupted) {
 		synchronized (lock) {
-			if (lastUtterance != null && !paused && Integer.parseInt(utteranceId) == lastUtterance.id) {
+			if (lastUtterance != null && !paused && Long.parseLong(utteranceId) == lastUtterance.id) {
 				GodotLib.ttsCallback(EVENT_CANCEL, lastUtterance.id, 0);
 				speaking = false;
 				updateTTS();
@@ -146,7 +146,7 @@ public void onStop(String utteranceId, boolean interrupted) {
 	@Override
 	public void onStart(String utteranceId) {
 		synchronized (lock) {
-			if (lastUtterance != null && lastUtterance.start == 0 && Integer.parseInt(utteranceId) == lastUtterance.id) {
+			if (lastUtterance != null && lastUtterance.start == 0 && Long.parseLong(utteranceId) == lastUtterance.id) {
 				GodotLib.ttsCallback(EVENT_START, lastUtterance.id, 0);
 			}
 		}
@@ -158,7 +158,7 @@ public void onStart(String utteranceId) {
 	@Override
 	public void onDone(String utteranceId) {
 		synchronized (lock) {
-			if (lastUtterance != null && !paused && Integer.parseInt(utteranceId) == lastUtterance.id) {
+			if (lastUtterance != null && !paused && Long.parseLong(utteranceId) == lastUtterance.id) {
 				GodotLib.ttsCallback(EVENT_END, lastUtterance.id, 0);
 				speaking = false;
 				updateTTS();
@@ -172,7 +172,7 @@ public void onDone(String utteranceId) {
 	@Override
 	public void onError(String utteranceId, int errorCode) {
 		synchronized (lock) {
-			if (lastUtterance != null && !paused && Integer.parseInt(utteranceId) == lastUtterance.id) {
+			if (lastUtterance != null && !paused && Long.parseLong(utteranceId) == lastUtterance.id) {
 				GodotLib.ttsCallback(EVENT_CANCEL, lastUtterance.id, 0);
 				speaking = false;
 				updateTTS();
@@ -186,7 +186,7 @@ public void onError(String utteranceId, int errorCode) {
 	@Override
 	public void onError(String utteranceId) {
 		synchronized (lock) {
-			if (lastUtterance != null && !paused && Integer.parseInt(utteranceId) == lastUtterance.id) {
+			if (lastUtterance != null && !paused && Long.parseLong(utteranceId) == lastUtterance.id) {
 				GodotLib.ttsCallback(EVENT_CANCEL, lastUtterance.id, 0);
 				speaking = false;
 				updateTTS();
@@ -222,7 +222,7 @@ public void onInit(int status) {
 	/**
 	 * Adds an utterance to the queue.
 	 */
-	public void speak(String text, String voice, int volume, float pitch, float rate, int utterance_id, boolean interrupt) {
+	public void speak(String text, String voice, int volume, float pitch, float rate, long utterance_id, boolean interrupt) {
 		synchronized (lock) {
 			if (state != INIT_STATE_SUCCESS) {
 				return;
diff --git a/platform/android/java/lib/src/main/java/org/godotengine/godot/tts/GodotUtterance.java b/platform/android/java/lib/src/main/java/org/godotengine/godot/tts/GodotUtterance.java
@@ -39,12 +39,12 @@ class GodotUtterance {
 	final int volume;
 	final float pitch;
 	final float rate;
-	final int id;
+	final long id;
 
 	int offset = -1;
 	int start = 0;
 
-	GodotUtterance(String text, String voice, int volume, float pitch, float rate, int id) {
+	GodotUtterance(String text, String voice, int volume, float pitch, float rate, long id) {
 		this.text = text;
 		this.voice = voice;
 		this.volume = volume;
diff --git a/platform/android/java_godot_lib_jni.cpp b/platform/android/java_godot_lib_jni.cpp
@@ -263,7 +263,7 @@ JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_back(JNIEnv *env, jcl
 	}
 }
 
-JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_ttsCallback(JNIEnv *env, jclass clazz, jint event, jint id, jint pos) {
+JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_ttsCallback(JNIEnv *env, jclass clazz, jint event, jlong id, jint pos) {
 	TTS_Android::_java_utterance_callback(event, id, pos);
 }
 
diff --git a/platform/android/java_godot_lib_jni.h b/platform/android/java_godot_lib_jni.h
@@ -42,7 +42,7 @@ JNIEXPORT jboolean JNICALL Java_org_godotengine_godot_GodotLib_setup(JNIEnv *env
 JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_resize(JNIEnv *env, jclass clazz, jobject p_surface, jint p_width, jint p_height);
 JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_newcontext(JNIEnv *env, jclass clazz, jobject p_surface);
 JNIEXPORT jboolean JNICALL Java_org_godotengine_godot_GodotLib_step(JNIEnv *env, jclass clazz);
-JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_ttsCallback(JNIEnv *env, jclass clazz, jint event, jint id, jint pos);
+JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_ttsCallback(JNIEnv *env, jclass clazz, jint event, jlong id, jint pos);
 JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_back(JNIEnv *env, jclass clazz);
 JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_dispatchMouseEvent(JNIEnv *env, jclass clazz, jint p_event_type, jint p_button_mask, jfloat p_x, jfloat p_y, jfloat p_delta_x, jfloat p_delta_y, jboolean p_double_click, jboolean p_source_mouse_relative, jfloat p_pressure, jfloat p_tilt_x, jfloat p_tilt_y);
 JNIEXPORT void JNICALL Java_org_godotengine_godot_GodotLib_dispatchTouchEvent(JNIEnv *env, jclass clazz, jint ev, jint pointer, jint pointer_count, jfloatArray positions, jboolean p_double_tap);
diff --git a/platform/android/tts_android.cpp b/platform/android/tts_android.cpp
@@ -52,7 +52,7 @@ jmethodID TTS_Android::_pause_speaking = nullptr;
 jmethodID TTS_Android::_resume_speaking = nullptr;
 jmethodID TTS_Android::_stop_speaking = nullptr;
 
-HashMap<int, Char16String> TTS_Android::ids;
+HashMap<int64_t, Char16String> TTS_Android::ids;
 
 void TTS_Android::_thread_function(void *self) {
 	JNIEnv *env = get_jni_env();
@@ -117,7 +117,7 @@ void TTS_Android::setup(jobject p_tts) {
 	_is_paused = env->GetMethodID(cls, "isPaused", "()Z");
 	_get_state = env->GetMethodID(cls, "getState", "()I");
 	_get_voices = env->GetMethodID(cls, "getVoices", "()[Ljava/lang/String;");
-	_speak = env->GetMethodID(cls, "speak", "(Ljava/lang/String;Ljava/lang/String;IFFIZ)V");
+	_speak = env->GetMethodID(cls, "speak", "(Ljava/lang/String;Ljava/lang/String;IFFJZ)V");
 	_pause_speaking = env->GetMethodID(cls, "pauseSpeaking", "()V");
 	_resume_speaking = env->GetMethodID(cls, "resumeSpeaking", "()V");
 	_stop_speaking = env->GetMethodID(cls, "stopSpeaking", "()V");
@@ -145,7 +145,7 @@ void TTS_Android::terminate() {
 	}
 }
 
-void TTS_Android::_java_utterance_callback(int p_event, int p_id, int p_pos) {
+void TTS_Android::_java_utterance_callback(int p_event, int64_t p_id, int p_pos) {
 	if (unlikely(!initialized)) {
 		initialize_tts();
 	}
@@ -230,7 +230,7 @@ Array TTS_Android::get_voices() {
 	return list;
 }
 
-void TTS_Android::speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
+void TTS_Android::speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {
 	if (unlikely(!initialized)) {
 		initialize_tts();
 	}
@@ -289,7 +289,7 @@ void TTS_Android::stop() {
 		initialize_tts();
 	}
 	ERR_FAIL_COND_MSG(!initialized || tts == nullptr, "Text to Speech not initialized.");
-	for (const KeyValue<int, Char16String> &E : ids) {
+	for (const KeyValue<int64_t, Char16String> &E : ids) {
 		DisplayServer::get_singleton()->tts_post_utterance_event(DisplayServer::TTS_UTTERANCE_CANCELED, E.key);
 	}
 	ids.clear();
diff --git a/platform/android/tts_android.h b/platform/android/tts_android.h
@@ -63,19 +63,19 @@ class TTS_Android {
 
 	static void _thread_function(void *self);
 
-	static HashMap<int, Char16String> ids;
+	static HashMap<int64_t, Char16String> ids;
 
 	static void initialize_tts(bool p_wait = true);
 
 public:
 	static void setup(jobject p_tts);
 	static void terminate();
-	static void _java_utterance_callback(int p_event, int p_id, int p_pos);
+	static void _java_utterance_callback(int p_event, int64_t p_id, int p_pos);
 
 	static bool is_speaking();
 	static bool is_paused();
 	static Array get_voices();
-	static void speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt);
+	static void speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt);
 	static void pause();
 	static void resume();
 	static void stop();
diff --git a/platform/linuxbsd/tts_linux.cpp b/platform/linuxbsd/tts_linux.cpp
@@ -207,7 +207,7 @@ Array TTS_Linux::get_voices() const {
 	return list;
 }
 
-void TTS_Linux::speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
+void TTS_Linux::speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {
 	_THREAD_SAFE_METHOD_
 
 	ERR_FAIL_NULL(synth);
diff --git a/platform/linuxbsd/tts_linux.h b/platform/linuxbsd/tts_linux.h
@@ -53,7 +53,7 @@ class TTS_Linux : public Object {
 	bool speaking = false;
 	bool paused = false;
 	int last_msg_id = -1;
-	HashMap<int, int> ids;
+	HashMap<int, int64_t> ids;
 
 	struct VoiceInfo {
 		String language;
@@ -82,7 +82,7 @@ class TTS_Linux : public Object {
 	bool is_paused() const;
 	Array get_voices() const;
 
-	void speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int p_utterance_id = 0, bool p_interrupt = false);
+	void speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int64_t p_utterance_id = 0, bool p_interrupt = false);
 	void pause();
 	void resume();
 	void stop();
diff --git a/platform/linuxbsd/wayland/display_server_wayland.cpp b/platform/linuxbsd/wayland/display_server_wayland.cpp
@@ -264,7 +264,7 @@ TypedArray<Dictionary> DisplayServerWayland::tts_get_voices() const {
 	return tts->get_voices();
 }
 
-void DisplayServerWayland::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
+void DisplayServerWayland::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {
 	if (unlikely(!tts)) {
 		initialize_tts();
 	}
diff --git a/platform/linuxbsd/wayland/display_server_wayland.h b/platform/linuxbsd/wayland/display_server_wayland.h
@@ -197,7 +197,7 @@ class DisplayServerWayland : public DisplayServer {
 	virtual bool tts_is_paused() const override;
 	virtual TypedArray<Dictionary> tts_get_voices() const override;
 
-	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int p_utterance_id = 0, bool p_interrupt = false) override;
+	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int64_t p_utterance_id = 0, bool p_interrupt = false) override;
 	virtual void tts_pause() override;
 	virtual void tts_resume() override;
 	virtual void tts_stop() override;
diff --git a/platform/linuxbsd/x11/display_server_x11.cpp b/platform/linuxbsd/x11/display_server_x11.cpp
@@ -409,7 +409,7 @@ TypedArray<Dictionary> DisplayServerX11::tts_get_voices() const {
 	return tts->get_voices();
 }
 
-void DisplayServerX11::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
+void DisplayServerX11::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {
 	if (unlikely(!tts)) {
 		initialize_tts();
 	}
diff --git a/platform/linuxbsd/x11/display_server_x11.h b/platform/linuxbsd/x11/display_server_x11.h
@@ -415,7 +415,7 @@ class DisplayServerX11 : public DisplayServer {
 	virtual bool tts_is_paused() const override;
 	virtual TypedArray<Dictionary> tts_get_voices() const override;
 
-	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int p_utterance_id = 0, bool p_interrupt = false) override;
+	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int64_t p_utterance_id = 0, bool p_interrupt = false) override;
 	virtual void tts_pause() override;
 	virtual void tts_resume() override;
 	virtual void tts_stop() override;
diff --git a/platform/macos/display_server_macos_base.h b/platform/macos/display_server_macos_base.h
@@ -80,7 +80,7 @@ class DisplayServerMacOSBase : public DisplayServer {
 	virtual bool tts_is_paused() const override;
 	virtual TypedArray<Dictionary> tts_get_voices() const override;
 
-	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int p_utterance_id = 0, bool p_interrupt = false) override;
+	virtual void tts_speak(const String &p_text, const String &p_voice, int p_volume = 50, float p_pitch = 1.f, float p_rate = 1.f, int64_t p_utterance_id = 0, bool p_interrupt = false) override;
 	virtual void tts_pause() override;
 	virtual void tts_resume() override;
 	virtual void tts_stop() override;
diff --git a/platform/macos/display_server_macos_base.mm b/platform/macos/display_server_macos_base.mm
@@ -128,7 +128,7 @@
 	return [tts getVoices];
 }
 
-void DisplayServerMacOSBase::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
+void DisplayServerMacOSBase::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {
 	if (unlikely(!tts)) {
 		initialize_tts();
 	}
diff --git a/platform/macos/tts_macos.h b/platform/macos/tts_macos.h
@@ -47,12 +47,12 @@
 @interface TTS_MacOS : NSObject <AVSpeechSynthesizerDelegate> {
 	// AVSpeechSynthesizer
 	bool speaking;
-	HashMap<id, int> ids;
+	HashMap<id, int64_t> ids;
 
 	// NSSpeechSynthesizer
 	bool paused;
 	bool have_utterance;
-	int last_utterance;
+	int64_t last_utterance;
 
 	id synth; // NSSpeechSynthesizer or AVSpeechSynthesizer
 	List<DisplayServer::TTSUtterance> queue;
@@ -63,6 +63,6 @@
 - (void)stopSpeaking;
 - (bool)isSpeaking;
 - (bool)isPaused;
-- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int)utterance_id interrupt:(bool)interrupt;
+- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int64_t)utterance_id interrupt:(bool)interrupt;
 - (Array)getVoices;
 @end
diff --git a/platform/macos/tts_macos.mm b/platform/macos/tts_macos.mm
@@ -148,9 +148,9 @@ - (void)update {
 			have_utterance = true;
 			[ns_synth startSpeakingString:[NSString stringWithUTF8String:message.text.utf8().get_data()]];
 		}
+		DisplayServer::get_singleton()->tts_post_utterance_event(DisplayServer::TTS_UTTERANCE_STARTED, message.id);
 		queue.pop_front();
 
-		DisplayServer::get_singleton()->tts_post_utterance_event(DisplayServer::TTS_UTTERANCE_STARTED, message.id);
 		speaking = true;
 	}
 }
@@ -210,7 +210,7 @@ - (bool)isPaused {
 	}
 }
 
-- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int)utterance_id interrupt:(bool)interrupt {
+- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int64_t)utterance_id interrupt:(bool)interrupt {
 	if (interrupt) {
 		[self stopSpeaking];
 	}
diff --git a/platform/web/display_server_web.cpp b/platform/web/display_server_web.cpp
diff --git a/platform/web/display_server_web.h b/platform/web/display_server_web.h
diff --git a/platform/web/godot_js.h b/platform/web/godot_js.h
diff --git a/platform/windows/display_server_windows.cpp b/platform/windows/display_server_windows.cpp
diff --git a/platform/windows/display_server_windows.h b/platform/windows/display_server_windows.h
diff --git a/platform/windows/tts_windows.cpp b/platform/windows/tts_windows.cpp
diff --git a/platform/windows/tts_windows.h b/platform/windows/tts_windows.h
diff --git a/servers/display/display_server.cpp b/servers/display/display_server.cpp
diff --git a/servers/display/display_server.h b/servers/display/display_server.h
diff --git a/servers/display/display_server_headless.h b/servers/display/display_server_headless.h

Original file line number	Diff line number	Diff line change
`@@ -413,7 +413,7 @@`
`413`	`413`	`return [tts getVoices];`
`414`	`414`	`}`
`415`	`415`
`416`		`-void DisplayServerAppleEmbedded::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {`
	`416`	`+void DisplayServerAppleEmbedded::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {`
`417`	`417`	`if (unlikely(!tts)) {`
`418`	`418`	`initialize_tts();`
`419`	`419`	`}`
Original file line number	Diff line number	Diff line change
`@@ -87,10 +87,9 @@ - (void)update {`
`87`	`87`
`88`	`88`	`ids[new_utterance] = message.id;`
`89`	`89`	`[av_synth speakUtterance:new_utterance];`
	`90`	`+ DisplayServer::get_singleton()->tts_post_utterance_event(DisplayServer::TTS_UTTERANCE_STARTED, message.id);`
`90`	`91`
`91`	`92`	`queue.pop_front();`
`92`		`-`
`93`		`- DisplayServer::get_singleton()->tts_post_utterance_event(DisplayServer::TTS_UTTERANCE_STARTED, message.id);`
`94`	`93`	`speaking = true;`
`95`	`94`	`}`
`96`	`95`	`}`
`@@ -120,7 +119,7 @@ - (bool)isPaused {`
`120`	`119`	`return [av_synth isPaused];`
`121`	`120`	`}`
`122`	`121`
`123`		`-- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int)utterance_id interrupt:(bool)interrupt {`
	`122`	`+- (void)speak:(const String &)text voice:(const String &)voice volume:(int)volume pitch:(float)pitch rate:(float)rate utterance_id:(int64_t)utterance_id interrupt:(bool)interrupt {`
`124`	`123`	`if (interrupt) {`
`125`	`124`	`[self stopSpeaking];`
`126`	`125`	`}`
Original file line number	Diff line number	Diff line change
`@@ -109,7 +109,7 @@ TypedArray<Dictionary> DisplayServerAndroid::tts_get_voices() const {`
`109`	`109`	`return TTS_Android::get_voices();`
`110`	`110`	`}`
`111`	`111`
`112`		`-void DisplayServerAndroid::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {`
	`112`	`+void DisplayServerAndroid::tts_speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int64_t p_utterance_id, bool p_interrupt) {`
`113`	`113`	`TTS_Android::speak(p_text, p_voice, p_volume, p_pitch, p_rate, p_utterance_id, p_interrupt);`
`114`	`114`	`}`
`115`	`115`