Fix speech playback on iOS Safari

voice.js

@@ -78,7 +78,10 @@
     let generation = 0;
     let recognition = null;
     let speechTimer = null;
+    let speechStartTimer = null;
     let listeningTimer = null;
+    let currentUtterance = null;
+    let speechPrimed = false;
 
     function setState(next, message = '') {
       state = next;
@@ -88,11 +91,34 @@
     function cancelSpeech() {
       generation += 1;
       if (speechTimer !== null) win.clearTimeout(speechTimer);
+      if (speechStartTimer !== null) win.clearTimeout(speechStartTimer);
       speechTimer = null;
-      try { win.speechSynthesis?.cancel(); } catch (_) { /* Best effort. */ }
+      speechStartTimer = null;
+      const wasQueued = currentUtterance !== null;
+      currentUtterance = null;
+      // WebKit versions before Safari 27 can discard a speak() queued in the
+      // same turn as cancel(). Do not clear an already-empty native queue.
+      if (wasQueued) {
+        try { win.speechSynthesis?.cancel(); } catch (_) { /* Best effort. */ }
+      }
       if (!recognition) setState('IDLE');
     }
 
+    function activateFromUserGesture() {
+      if (!win.speechSynthesis || !win.SpeechSynthesisUtterance) return false;
+      if (speechPrimed) return true;
+      // iOS Safari requires speech output to be initiated by a user gesture.
+      // Prime its speech channel silently on the first trusted tap/key press so
+      // later game replies can be spoken after the API response arrives.
+      try {
+        const primer = new win.SpeechSynthesisUtterance(' ');
+        primer.volume = 0;
+        win.speechSynthesis.speak(primer);
+        speechPrimed = true;
+        return true;
+      } catch (_) { return false; }
+    }
+
     function finishRecognition(token, message = '') {
       if (token !== generation) return;
       if (listeningTimer !== null) win.clearTimeout(listeningTimer);
@@ -181,8 +207,9 @@
     function speak(text, voiceOptions = {}) {
       if (!text || !win.speechSynthesis || !win.SpeechSynthesisUtterance) return false;
       stopListening();
-      cancelSpeech();
-      const token = generation;
+      const hadQueuedUtterance = currentUtterance !== null;
+      if (hadQueuedUtterance) cancelSpeech();
+      const token = ++generation;
       let utterance;
       try { utterance = new win.SpeechSynthesisUtterance(text); }
       catch (_) { setState('IDLE', 'Talsyntesen kunde inte startas. Dialogen finns kvar som text.'); return false; }
@@ -198,28 +225,63 @@
       utterance.voice = voices.find(voice => voice.name === requestedName)
         || voices.find(voice => /^sv(-|$)/i.test(voice.lang))
         || null;
+      utterance.onstart = () => {
+        if (token !== generation) return;
+        if (speechStartTimer !== null) win.clearTimeout(speechStartTimer);
+        speechStartTimer = null;
+        if (typeof voiceOptions.onStart === 'function') voiceOptions.onStart();
+      };
       utterance.onend = () => {
         if (token !== generation) return;
         if (speechTimer !== null) win.clearTimeout(speechTimer);
+        if (speechStartTimer !== null) win.clearTimeout(speechStartTimer);
         speechTimer = null;
+        speechStartTimer = null;
+        currentUtterance = null;
         setState('IDLE');
       };
       utterance.onerror = () => {
         if (token !== generation) return;
         if (speechTimer !== null) win.clearTimeout(speechTimer);
+        if (speechStartTimer !== null) win.clearTimeout(speechStartTimer);
         speechTimer = null;
+        speechStartTimer = null;
+        currentUtterance = null;
         generation += 1;
         setState('IDLE', 'Uppläsningen avbröts. Dialogen finns kvar som text.');
       };
       setState('SPEAKING', 'Läser upp dialog.');
+      currentUtterance = utterance;
+      speechStartTimer = win.setTimeout(() => {
+        if (token !== generation || currentUtterance !== utterance) return;
+        speechStartTimer = null;
+        setState('IDLE', 'Uppläsningen startade inte. Tryck på Läs senaste repliken för att starta ljudet.');
+      }, 4000);
       speechTimer = win.setTimeout(() => {
         if (token !== generation) return;
         generation += 1;
         try { win.speechSynthesis.cancel(); } catch (_) { /* Best effort. */ }
+        currentUtterance = null;
+        if (speechStartTimer !== null) win.clearTimeout(speechStartTimer);
+        speechStartTimer = null;
         speechTimer = null;
         setState('IDLE', 'Uppläsningen avslutades. Dialogen finns kvar som text.');
       }, Math.max(30000, Math.min(180000, String(text).length * 180)));
-      try { win.speechSynthesis.speak(utterance); }
+      const enqueue = () => {
+        if (token !== generation) return;
+        try { win.speechSynthesis.speak(utterance); }
+        catch (_) {
+          currentUtterance = null;
+          cancelSpeech();
+          setState('IDLE', 'Talsyntesen kunde inte startas. Dialogen finns kvar som text.');
+        }
+      };
+      try {
+        // Give WebKit one event-loop turn to finish cancel() before replacing
+        // speech that was actively playing. Normal replies enqueue immediately.
+        if (hadQueuedUtterance) win.setTimeout(enqueue, 100);
+        else enqueue();
+      }
       catch (_) { cancelSpeech(); setState('IDLE', 'Talsyntesen kunde inte startas. Dialogen finns kvar som text.'); return false; }
       return true;
     }
@@ -230,7 +292,7 @@
     function getSettings() { return {...settings}; }
     function getVoices() { return availableVoices(); }
     function supportsRecognition() { return Boolean(win.SpeechRecognition || win.webkitSpeechRecognition); }
-    return {startListening, stopListening, speak, cancelSpeech, stopAll, update, getState, getSettings, getVoices, supportsRecognition};
+    return {startListening, stopListening, speak, cancelSpeech, stopAll, activateFromUserGesture, update, getState, getSettings, getVoices, supportsRecognition};
   }
 
   root.GameVoice = {createVoiceController, DEFAULT_SETTINGS, parseVoiceCommand, loadSettings, saveSettings, characterVoiceProfile};