@iternio/react-native-tts 4.1.2 → 4.1.4

package/android/src/main/java/net/no_mad/tts/TextToSpeechModule.java

@@ -1,19 +1,28 @@
 package net.no_mad.tts;
 
+import android.content.ActivityNotFoundException;
+import android.content.Intent;
+import android.content.pm.PackageInfo;
+import android.content.pm.PackageManager;
+import android.content.pm.PackageManager.NameNotFoundException;
+import android.media.AudioAttributes;
+import android.media.AudioFocusRequest;
 import android.media.AudioManager;
+import android.net.Uri;
 import android.os.Build;
 import android.os.Bundle;
-import android.content.Intent;
-import android.content.ActivityNotFoundException;
-import android.app.Activity;
-import android.net.Uri;
 import android.speech.tts.TextToSpeech;
 import android.speech.tts.UtteranceProgressListener;
 import android.speech.tts.Voice;
-import android.content.pm.PackageInfo;
-import android.content.pm.PackageManager;
-import android.content.pm.PackageManager.NameNotFoundException;
-import com.facebook.react.bridge.*;
+
+import com.facebook.react.bridge.Arguments;
+import com.facebook.react.bridge.Promise;
+import com.facebook.react.bridge.ReactApplicationContext;
+import com.facebook.react.bridge.ReactContextBaseJavaModule;
+import com.facebook.react.bridge.ReactMethod;
+import com.facebook.react.bridge.ReadableMap;
+import com.facebook.react.bridge.WritableArray;
+import com.facebook.react.bridge.WritableMap;
 import com.facebook.react.modules.core.DeviceEventManagerModule;
 
 import java.util.ArrayList;
@@ -29,14 +38,21 @@ public class TextToSpeechModule extends ReactContextBaseJavaModule {
 
     private boolean ducking = false;
     private AudioManager audioManager;
-    private AudioManager.OnAudioFocusChangeListener afChangeListener;
+    private AudioManager.OnAudioFocusChangeListener afChangeListener = i -> {};
 
     private Map<String, Locale> localeCountryMap;
     private Map<String, Locale> localeLanguageMap;
 
+    private AudioAttributes audioAttributes;
+
     public TextToSpeechModule(ReactApplicationContext reactContext) {
         super(reactContext);
         audioManager = (AudioManager) reactContext.getApplicationContext().getSystemService(reactContext.AUDIO_SERVICE);
+        audioAttributes = new AudioAttributes.Builder()
+                .setContentType(AudioAttributes.CONTENT_TYPE_SPEECH)
+                .setUsage(AudioAttributes.USAGE_ASSISTANCE_NAVIGATION_GUIDANCE)
+                .build();
+
         initStatusPromises = new ArrayList<Promise>();
         //initialize ISO3, ISO2 languague country code mapping.
         initCountryLanguageCodeMapping();
@@ -97,6 +113,7 @@ public class TextToSpeechModule extends ReactContextBaseJavaModule {
                     params.putInt("start", start);
                     params.putInt("end", end);
                     params.putInt("frame", frame);
+                    params.putInt("length", end - start);
                     sendEvent("tts-progress", params);
                 }
             });
@@ -210,12 +227,23 @@ public class TextToSpeechModule extends ReactContextBaseJavaModule {
         if(notReady(promise)) return;
 
         if(ducking) {
+            int amResult;
             // Request audio focus for playback
-            int amResult = audioManager.requestAudioFocus(afChangeListener,
-                                                          // Use the music stream.
-                                                          AudioManager.STREAM_MUSIC,
-                                                          // Request permanent focus.
-                                                          AudioManager.AUDIOFOCUS_GAIN_TRANSIENT_MAY_DUCK);
+            if (android.os.Build.VERSION.SDK_INT >= android.os.Build.VERSION_CODES.O) {
+                AudioFocusRequest audioFocusRequest = new AudioFocusRequest.Builder(AudioManager.AUDIOFOCUS_GAIN_TRANSIENT_MAY_DUCK)
+                        .setAudioAttributes(audioAttributes)
+                        .setAcceptsDelayedFocusGain(false)
+                        .setOnAudioFocusChangeListener(afChangeListener)
+                        .build();
+
+                amResult = audioManager.requestAudioFocus(audioFocusRequest);
+            } else {
+                amResult = audioManager.requestAudioFocus(afChangeListener,
+                        // Use the music stream.
+                        AudioManager.STREAM_MUSIC,
+                        // Request permanent focus.
+                        AudioManager.AUDIOFOCUS_GAIN_TRANSIENT_MAY_DUCK);
+            }
 
             if(amResult != AudioManager.AUDIOFOCUS_REQUEST_GRANTED) {
                 promise.reject("Android AudioManager error, failed to request audio focus");
@@ -311,6 +339,18 @@ public class TextToSpeechModule extends ReactContextBaseJavaModule {
         }
     }
 
+    @ReactMethod
+    public void getDefaultVoiceIdentifier(String language, Promise promise) {
+        if(notReady(promise)) return;
+
+        Voice currentVoice = tts.getVoice();
+        if (currentVoice == null) {
+            promise.reject("not_found", "Language not found");
+            return;
+        }
+        promise.resolve(currentVoice.getName());
+    }
+
     @ReactMethod
     public void voices(Promise promise) {
         if(notReady(promise)) return;
@@ -498,6 +538,8 @@ public class TextToSpeechModule extends ReactContextBaseJavaModule {
                 audioStreamType = AudioManager.USE_DEFAULT_STREAM_TYPE;
         }
 
+        tts.setAudioAttributes(audioAttributes);
+
         if (Build.VERSION.SDK_INT >= 21) {
             Bundle params = new Bundle();
             params.putInt(TextToSpeech.Engine.KEY_PARAM_STREAM, audioStreamType);

package/index.d.ts

@@ -62,7 +62,7 @@ export type Engine = {
 
 export type AndroidOptions = {
   /** Parameter key to specify the audio stream type to be used when speaking text or playing back a file */
-  KEY_PARAM_STREAM:
+  KEY_PARAM_STREAM?:
     | "STREAM_VOICE_CALL"
     | "STREAM_SYSTEM"
     | "STREAM_RING"
@@ -72,17 +72,17 @@ export type AndroidOptions = {
     | "STREAM_DTMF"
     | "STREAM_ACCESSIBILITY";
   /** Parameter key to specify the speech volume relative to the current stream type volume used when speaking text. Volume is specified as a float ranging from 0 to 1 where 0 is silence, and 1 is the maximum volume (the default behavior). */
-  KEY_PARAM_VOLUME: number;
+  KEY_PARAM_VOLUME?: number;
   /** Parameter key to specify how the speech is panned from left to right when speaking text. Pan is specified as a float ranging from -1 to +1 where -1 maps to a hard-left pan, 0 to center (the default behavior), and +1 to hard-right. */
-  KEY_PARAM_PAN: number;
+  KEY_PARAM_PAN?: number;
 };
 
 export type Options =
   | string
   | {
-      iosVoiceId: string;
-      rate: number;
-      androidParams: AndroidOptions;
+      iosVoiceId?: string;
+      rate?: number;
+      androidParams?: AndroidOptions;
     };
 
 export class ReactNativeTts extends RN.NativeEventEmitter {
@@ -97,9 +97,10 @@ export class ReactNativeTts extends RN.NativeEventEmitter {
   setDefaultLanguage: (language: string) => Promise<"success">;
   setIgnoreSilentSwitch: (ignoreSilentSwitch: IOSSilentSwitchBehavior) => Promise<boolean>;
   voices: () => Promise<Voice[]>;
+  getDefaultVoiceIdentifier: (language: String) => Promise<String>;
   engines: () => Promise<Engine[]>;
   /** Read the sentence and return an id for the task. */
-  speak: (utterance: string, options?: Options) => string | number;
+  speak: (utterance: string, options?: Options) => Promise<string | number>;
   stop: (onWordBoundary?: boolean) => Promise<boolean>;
   pause: (onWordBoundary?: boolean) => Promise<boolean>;
   resume: () => Promise<boolean>;

package/index.js

@@ -69,6 +69,10 @@ class Tts extends NativeEventEmitter {
     return TextToSpeech.voices();
   }
 
+  getDefaultVoiceIdentifier(language) {
+    return TextToSpeech.getDefaultVoiceIdentifier(language);
+  }
+
   engines() {
     if (Platform.OS === 'ios' || Platform.OS === 'windows') {
       return Promise.resolve([]);

package/ios/TextToSpeech/TextToSpeech.h

@@ -17,4 +17,7 @@
 @property (nonatomic) float defaultRate;
 @property (nonatomic) float defaultPitch;
 @property (nonatomic) bool ducking;
+
+// Singleton accessor for New Architecture compatibility
++ (instancetype)sharedInstance;
 @end

package/ios/TextToSpeech/TextToSpeech.m

@@ -12,6 +12,9 @@
 
 #import "TextToSpeech.h"
 
+// Singleton instance for New Architecture compatibility
+static TextToSpeech *_sharedInstance = nil;
+
 @implementation TextToSpeech {
     NSString * _ignoreSilentSwitch;
 }
@@ -20,6 +23,11 @@
 
 RCT_EXPORT_MODULE()
 
++ (instancetype)sharedInstance
+{
+    return _sharedInstance;
+}
+
 -(NSArray<NSString *> *)supportedEvents
 {
     return @[@"tts-start", @"tts-finish", @"tts-pause", @"tts-resume", @"tts-progress", @"tts-cancel"];
@@ -27,12 +35,19 @@ RCT_EXPORT_MODULE()
 
 -(instancetype)init
 {
+    // If we already have a shared instance, return it instead of creating a new one
+    // This ensures singleton behavior in React Native New Architecture
+    if (_sharedInstance != nil) {
+        return _sharedInstance;
+    }
+    
     self = [super init];
     if (self) {
         _synthesizer = [AVSpeechSynthesizer new];
         _synthesizer.delegate = self;
         _ducking = false;
         _ignoreSilentSwitch = @"inherit"; // inherit, ignore, obey
+        _sharedInstance = self;
     }
 
     return self;
@@ -79,11 +94,16 @@ RCT_EXPORT_METHOD(speak:(NSString *)text
     }
 
     if([_ignoreSilentSwitch isEqualToString:@"ignore"]) {
+        // Build options based on ducking setting
+        AVAudioSessionCategoryOptions options = AVAudioSessionCategoryOptionInterruptSpokenAudioAndMixWithOthers;
+        if (_ducking) {
+            options |= AVAudioSessionCategoryOptionDuckOthers;
+        }
+        
         [[AVAudioSession sharedInstance]
          setCategory:AVAudioSessionCategoryPlayback
          mode:AVAudioSessionModeVoicePrompt
-         // This will pause a spoken audio like podcast or audiobook and duck the volume for music
-         options:AVAudioSessionCategoryOptionInterruptSpokenAudioAndMixWithOthers
+         options:options
          error:nil
         ];
     } else if([_ignoreSilentSwitch isEqualToString:@"obey"]) {
@@ -132,23 +152,23 @@ RCT_EXPORT_METHOD(resume:(RCTPromiseResolveBlock)resolve reject:(__unused RCTPro
 }
 
 
-RCT_EXPORT_METHOD(setDucking:(bool *)ducking
+RCT_EXPORT_METHOD(setDucking:(BOOL)ducking
                   resolve:(RCTPromiseResolveBlock)resolve
                   reject:(__unused RCTPromiseRejectBlock)reject)
 {
-    _ducking = ducking;
+    _ducking = (bool)ducking;
 
     if(ducking) {
         AVAudioSession *session = [AVAudioSession sharedInstance];
         [session setCategory:AVAudioSessionCategoryPlayback
-                 withOptions:AVAudioSessionCategoryOptionDuckOthers
+                        mode:AVAudioSessionModeVoicePrompt
+                     options:(AVAudioSessionCategoryOptionDuckOthers|AVAudioSessionCategoryOptionInterruptSpokenAudioAndMixWithOthers)
                        error:nil];
     }
 
     resolve(@"success");
 }
 
-
 RCT_EXPORT_METHOD(setDefaultLanguage:(NSString *)language
                   resolve:(RCTPromiseResolveBlock)resolve
                   reject:(RCTPromiseRejectBlock)reject)
@@ -212,18 +232,40 @@ RCT_EXPORT_METHOD(setIgnoreSilentSwitch:(NSString *)ignoreSilentSwitch
     }
 }
 
+RCT_EXPORT_METHOD(getDefaultVoiceIdentifier:(NSString *)language
+                  resolve:(RCTPromiseResolveBlock)resolve
+                  reject:(RCTPromiseRejectBlock)reject)
+{
+    AVSpeechSynthesisVoice *voice = [AVSpeechSynthesisVoice voiceWithLanguage:language];
+
+    if(voice) {
+        resolve(voice.identifier);
+    } else {
+        reject(@"not_found", @"Language not found", nil);
+    }
+}
+
 RCT_EXPORT_METHOD(voices:(RCTPromiseResolveBlock)resolve
                   reject:(__unused RCTPromiseRejectBlock)reject)
 {
     NSMutableArray *voices = [NSMutableArray new];
 
     for (AVSpeechSynthesisVoice *voice in [AVSpeechSynthesisVoice speechVoices]) {
-        [voices addObject:@{
-            @"id": voice.identifier,
-            @"name": voice.name,
-            @"language": voice.language,
-            @"quality": (voice.quality == AVSpeechSynthesisVoiceQualityEnhanced) ? @500 : @300
-        }];
+        if (@available(iOS 16.0, *)) {
+            [voices addObject:@{
+                @"id": voice.identifier,
+                @"name": voice.name,
+                @"language": voice.language,
+                @"quality": (voice.quality == AVSpeechSynthesisVoiceQualityEnhanced) ? @500 : (voice.quality == AVSpeechSynthesisVoiceQualityPremium) ? @800 : @300
+            }];
+        } else {
+            [voices addObject:@{
+                @"id": voice.identifier,
+                @"name": voice.name,
+                @"language": voice.language,
+                @"quality": (voice.quality == AVSpeechSynthesisVoiceQualityEnhanced) ? @500 : @300
+            }];
+        }
     }
 
     resolve(voices);
@@ -232,7 +274,9 @@ RCT_EXPORT_METHOD(voices:(RCTPromiseResolveBlock)resolve
 -(void)speechSynthesizer:(AVSpeechSynthesizer *)synthesizer didStartSpeechUtterance:(AVSpeechUtterance *)utterance
 {
     if(_ducking) {
-        [[AVAudioSession sharedInstance] setActive:true error:nil];
+        dispatch_async(dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^{
+            [[AVAudioSession sharedInstance] setActive:true error:nil];
+        });
     }
 
     [self sendEventWithName:@"tts-start" body:@{@"utteranceId":[NSNumber numberWithUnsignedLong:utterance.hash]}];
@@ -241,7 +285,9 @@ RCT_EXPORT_METHOD(voices:(RCTPromiseResolveBlock)resolve
 -(void)speechSynthesizer:(AVSpeechSynthesizer *)synthesizer didFinishSpeechUtterance:(AVSpeechUtterance *)utterance
 {
     if(_ducking) {
-        [[AVAudioSession sharedInstance] setActive:false error:nil];
+        dispatch_async(dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^{
+            [[AVAudioSession sharedInstance] setActive:false error:nil];
+        });
     }
 
     [self sendEventWithName:@"tts-finish" body:@{@"utteranceId":[NSNumber numberWithUnsignedLong:utterance.hash]}];
@@ -250,7 +296,9 @@ RCT_EXPORT_METHOD(voices:(RCTPromiseResolveBlock)resolve
 -(void)speechSynthesizer:(AVSpeechSynthesizer *)synthesizer didPauseSpeechUtterance:(AVSpeechUtterance *)utterance
 {
     if(_ducking) {
-        [[AVAudioSession sharedInstance] setActive:false error:nil];
+        dispatch_async(dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^{
+            [[AVAudioSession sharedInstance] setActive:false error:nil];
+        });
     }
 
     [self sendEventWithName:@"tts-pause" body:@{@"utteranceId":[NSNumber numberWithUnsignedLong:utterance.hash]}];
@@ -259,7 +307,9 @@ RCT_EXPORT_METHOD(voices:(RCTPromiseResolveBlock)resolve
 -(void)speechSynthesizer:(AVSpeechSynthesizer *)synthesizer didContinueSpeechUtterance:(AVSpeechUtterance *)utterance
 {
     if(_ducking) {
-        [[AVAudioSession sharedInstance] setActive:true error:nil];
+        dispatch_async(dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^{
+            [[AVAudioSession sharedInstance] setActive:true error:nil];
+        });
     }
 
     [self sendEventWithName:@"tts-resume" body:@{@"utteranceId":[NSNumber numberWithUnsignedLong:utterance.hash]}];
@@ -276,7 +326,9 @@ RCT_EXPORT_METHOD(voices:(RCTPromiseResolveBlock)resolve
 -(void)speechSynthesizer:(AVSpeechSynthesizer *)synthesizer didCancelSpeechUtterance:(AVSpeechUtterance *)utterance
 {
     if(_ducking) {
-        [[AVAudioSession sharedInstance] setActive:false error:nil];
+        dispatch_async(dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^{
+            [[AVAudioSession sharedInstance] setActive:false error:nil];
+        });
     }
 
     [self sendEventWithName:@"tts-cancel" body:@{@"utteranceId":[NSNumber numberWithUnsignedLong:utterance.hash]}];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@iternio/react-native-tts",
-  "version": "4.1.2",
+  "version": "4.1.4",
   "description": "React Native Text-To-Speech module for Android and iOS",
   "main": "index.js",
   "repository": {