System wide STT service

README.md

@@ -40,6 +40,10 @@ Currently Dicio answers questions about:
 ## Speech to text
 
 Dicio uses [Vosk](https://github.com/alphacep/vosk-api/) as its speech to text (`STT`) engine. In order to be able to run on every phone small models are employed, weighing `~50MB`. The download from [here](https://alphacephei.com/vosk/models) starts automatically whenever needed, so the app language can be changed seamlessly.
+Dicio exports vosk as a speech-to-text service to the android system. Other apps can query this by different ways:
+- [Via an intent](https://developer.android.com/reference/android/speech/RecognizerIntent), which shows up a dicio UI for speech input. The result is then provided to the requesting app (automatically of after user agreed as set in dicio settings).
+- [From background](https://developer.android.com/reference/android/speech/SpeechRecognizer), if the requesting app has the record audio permission and dicio is set as speech input within settings -> apps -> default apps -> assistant (the exact path may vary depending on the Android version)
+- If you want to use it as a "speech keyboard" (IME), you currently still need an app which use the Android speech-to-text-service and provides an IME (e.g. [this one](https://github.com/Kaljurand/K6nele))
 
 ## Contributing
 
@@ -57,7 +61,6 @@ When contributing keep in mind that other people may have **needs** and **views
 If you want to translate Dicio to a new language you have to follow these **steps**:
 <ul><li>
   Translate the <b>strings used inside the app</b> via <a href="https://hosted.weblate.org/engage/dicio-android/">Weblate</a>. If your language isn't already there, add it with <a href="https://hosted.weblate.org/new-lang/dicio-android/strings/">tool -> start new translation</a>.
-  </br>
   <a href="https://hosted.weblate.org/engage/dicio-android/">
   <img src="https://hosted.weblate.org/widgets/dicio-android/-/287x66-grey.png" alt="Translation status" />
   </a>

app/src/main/AndroidManifest.xml

@@ -1,46 +1,51 @@
 <?xml version="1.0" encoding="utf-8"?>
 <manifest xmlns:android="http://schemas.android.com/apk/res/android"
     xmlns:tools="http://schemas.android.com/tools"
-    android:installLocation="auto"> <!-- Allow installing also on external storage -->
+    android:installLocation="auto" >
 
+    <!-- Allow installing also on external storage -->
     <uses-permission android:name="android.permission.INTERNET" />
     <uses-permission android:name="android.permission.RECORD_AUDIO" />
-
     <!-- required by the download manager for APIs < Q -->
     <uses-permission
         android:name="android.permission.WRITE_EXTERNAL_STORAGE"
         android:maxSdkVersion="28" />
-
     <!-- the open skill needs to query all apps -->
     <uses-permission
         android:name="android.permission.QUERY_ALL_PACKAGES"
         tools:ignore="QueryAllPackagesPermission" />
-
     <!-- the telephone skill needs to query contacts and call them -->
     <uses-permission android:name="android.permission.READ_CONTACTS" />
     <uses-permission android:name="android.permission.CALL_PHONE" />
 
+    <queries><!--To access Speech recognizer via system interface on Android 11+
+     https://developer.android.com/reference/android/speech/SpeechRecognizer#createSpeechRecognizer(android.content.Context,%20android.content.ComponentName)-->
+        <intent>
+            <action
+                android:name="android.speech.RecognitionService" />
+        </intent>
+    </queries>
+
     <application
         android:name=".App"
         android:allowBackup="true"
+        android:dataExtractionRules="@xml/data_extraction_rules"
         android:fullBackupContent="@xml/full_backup_content"
         android:icon="@mipmap/ic_launcher"
         android:label="@string/app_name"
         android:supportsRtl="true"
         android:theme="@style/DarkAppTheme"
-        tools:ignore="GoogleAppIndexingWarning"
-        android:dataExtractionRules="@xml/data_extraction_rules">
+        tools:ignore="GoogleAppIndexingWarning" >
 
         <activity
             android:name=".MainActivity"
             android:exported="true"
             android:theme="@style/SplashScreenTheme"
-            android:windowSoftInputMode="stateUnspecified|adjustResize">
+            android:windowSoftInputMode="stateUnspecified|adjustResize" >
             <intent-filter>
                 <action android:name="android.intent.action.MAIN" />
                 <category android:name="android.intent.category.LAUNCHER" />
             </intent-filter>
-
             <intent-filter>
                 <action android:name="android.intent.action.ASSIST" />
                 <category android:name="android.intent.category.DEFAULT" />
@@ -50,28 +55,44 @@
                 android:name="com.android.systemui.action_assist_icon"
                 android:resource="@mipmap/ic_launcher" />
         </activity>
-
         <activity
             android:name=".settings.SettingsActivity"
             android:exported="false" />
-
         <activity
             android:name=".error.ErrorActivity"
             android:exported="false" />
-
         <activity
             android:name=".input.stt_service.SttServiceActivity"
-            android:taskAffinity=""
             android:excludeFromRecents="true"
             android:exported="true"
+            android:taskAffinity=""
             android:theme="@style/SttServiceDarkAppTheme"
-            android:windowSoftInputMode="adjustResize">
-
+            android:windowSoftInputMode="adjustResize" >
             <intent-filter>
                 <category android:name="android.intent.category.DEFAULT" />
                 <action android:name="android.speech.action.RECOGNIZE_SPEECH" />
             </intent-filter>
         </activity>
 
+        <service
+            android:name=".input.stt_service.SttService"
+            android:enabled="true"
+            android:exported="true"
+            android:description="@string/pref_input_method_vosk"
+            android:icon="@mipmap/ic_launcher"
+        >
+<!-- TODO check the following tags whether these are helpful too           -->
+        <!--            android:directBootAware=["true" | "false"]-->
+        <!--        android:foregroundServiceType="microphone" -->
+        <!--        android:label="string resource"-->
+            <intent-filter>
+                <action android:name="android.speech.RecognitionService"/>
+                <category android:name="android.intent.category.DEFAULT" />
+            </intent-filter>
+            <meta-data
+                android:name="android.speech"
+                android:resource="@xml/stt_service_metadata" />
+        </service>
     </application>
+
 </manifest>

app/src/main/java/org/stypox/dicio/MainActivity.java

@@ -1,8 +1,5 @@
 package org.stypox.dicio;
 
-import static android.Manifest.permission.RECORD_AUDIO;
-import static android.content.pm.PackageManager.PERMISSION_GRANTED;
-
 import android.content.Intent;
 import android.content.SharedPreferences;
 import android.os.Bundle;
@@ -13,23 +10,16 @@
 import android.widget.ProgressBar;
 import android.widget.ScrollView;
 
-import androidx.annotation.NonNull;
-import androidx.annotation.Nullable;
-import androidx.appcompat.app.ActionBarDrawerToggle;
-import androidx.appcompat.widget.SearchView;
-import androidx.appcompat.widget.Toolbar;
-import androidx.core.app.ActivityCompat;
-import androidx.core.view.GravityCompat;
-import androidx.drawerlayout.widget.DrawerLayout;
-import androidx.preference.PreferenceManager;
-
 import com.google.android.material.floatingactionbutton.ExtendedFloatingActionButton;
 import com.google.android.material.navigation.NavigationView;
 
+import org.dicio.skill.output.GraphicalOutputDevice;
+import org.dicio.skill.output.SpeechOutputDevice;
 import org.stypox.dicio.eval.SkillEvaluator;
 import org.stypox.dicio.eval.SkillRanker;
 import org.stypox.dicio.input.InputDevice;
 import org.stypox.dicio.input.SpeechInputDevice;
+import org.stypox.dicio.input.AndroidSttServiceInputDevice;
 import org.stypox.dicio.input.ToolbarInputDevice;
 import org.stypox.dicio.input.VoskInputDevice;
 import org.stypox.dicio.input.stt_service.SttServiceActivity;
@@ -42,8 +32,19 @@
 import org.stypox.dicio.skills.SkillHandler;
 import org.stypox.dicio.util.BaseActivity;
 import org.stypox.dicio.util.PermissionUtils;
-import org.dicio.skill.output.GraphicalOutputDevice;
-import org.dicio.skill.output.SpeechOutputDevice;
+
+import androidx.annotation.NonNull;
+import androidx.annotation.Nullable;
+import androidx.appcompat.app.ActionBarDrawerToggle;
+import androidx.appcompat.widget.SearchView;
+import androidx.appcompat.widget.Toolbar;
+import androidx.core.app.ActivityCompat;
+import androidx.core.view.GravityCompat;
+import androidx.drawerlayout.widget.DrawerLayout;
+import androidx.preference.PreferenceManager;
+
+import static android.Manifest.permission.RECORD_AUDIO;
+import static android.content.pm.PackageManager.PERMISSION_GRANTED;
 
 public class MainActivity extends BaseActivity
         implements NavigationView.OnNavigationItemSelectedListener {
@@ -304,6 +305,11 @@ private InputDevice buildPrimaryInputDevice() {
                 .getString(getString(R.string.pref_key_input_method), "");
         if (preference.equals(getString(R.string.pref_val_input_method_text))) {
             return new ToolbarInputDevice();
+        } else if (preference.equals(getString(R.string.pref_val_input_method_systemStt))) {
+            //TODO make a hint/data privacy warning etc. in preference when this one is chosen that
+            // the speech dicio records is given to a third party app according to system
+            // settings
+            return new AndroidSttServiceInputDevice(this);
         } else { // default
             return new VoskInputDevice(this);
         }