Merge remote-tracking branch 'origin/dev' into dev

app/build.gradle.kts

@@ -16,8 +16,10 @@ android {
         targetSdk = 36
         versionCode = 1
         versionName = "1.0"
-
         testInstrumentationRunner = "androidx.test.runner.AndroidJUnitRunner"
+        ndk {
+            abiFilters.addAll(listOf("armeabi-v7a", "arm64-v8a", "x86", "x86_64"))
+        }
     }
 
     buildTypes {
@@ -36,10 +38,13 @@ android {
 }
 
 dependencies {
+    implementation("net.java.dev.jna:jna:5.13.0@aar")
+    //implementation("org.vosk:vosk-android:0.3.45")
     // OkHttp für Netzwerkanfragen an Telegram
-    implementation("com.alphacephei:vosk-android:0.3.45")
+    implementation("com.alphacephei:vosk-android:0.3.45"){
+        exclude(group = "net.java.dev.jna", module = "jna")
+    }
     implementation("com.squareup.okhttp3:okhttp:4.12.0")
-    //implementation ("ai.picovoice:porcupine-android:3.0.2")
     // Coroutinen für Hintergrund-Prozesse (Polling)
     implementation("org.jetbrains.kotlinx:kotlinx-coroutines-android:1.7.3")
     implementation(libs.androidx.core.ktx)

app/src/main/AndroidManifest.xml

@@ -1,31 +1,37 @@
-<?xml version="1.0" encoding="utf-8"?>
 <manifest xmlns:android="http://schemas.android.com/apk/res/android"
-    xmlns:tools="http://schemas.android.com/tools">
+    package="com.example.jarvis_stts">
+
     <uses-permission android:name="android.permission.INTERNET" />
     <uses-permission android:name="android.permission.RECORD_AUDIO" />
-    <uses-permission android:name="android.permission.INTERNET" />
     <uses-permission android:name="android.permission.FOREGROUND_SERVICE" />
     <uses-permission android:name="android.permission.FOREGROUND_SERVICE_MICROPHONE" />
+    <uses-permission android:name="android.permission.POST_NOTIFICATIONS" />
+    <uses-permission android:name="android.permission.SYSTEM_ALERT_WINDOW"/>
 
     <application
-        android:usesCleartextTraffic="true"
+
         android:allowBackup="true"
-        android:dataExtractionRules="@xml/data_extraction_rules"
-        android:fullBackupContent="@xml/backup_rules"
         android:icon="@mipmap/ic_launcher"
         android:label="@string/app_name"
         android:roundIcon="@mipmap/ic_launcher_round"
         android:supportsRtl="true"
-        android:theme="@style/Theme.Jarvisstts">
+        android:theme="@style/Theme.AppCompat.DayNight.NoActionBar"
+        android:usesCleartextTraffic="true">
+
         <activity
             android:name=".MainActivity"
-            android:exported="true">
+            android:exported="true"
+            android:launchMode="singleTask">
             <intent-filter>
                 <action android:name="android.intent.action.MAIN" />
-
                 <category android:name="android.intent.category.LAUNCHER" />
             </intent-filter>
         </activity>
-    </application>
 
+        <service
+            android:name=".JarvisService"
+            android:enabled="true"
+            android:exported="false"
+            android:foregroundServiceType="microphone" />
+    </application>
 </manifest>

app/src/main/assets/model-de/COPYING

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. this License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

app/src/main/assets/model-de/README

@@ -0,0 +1,12 @@
+German model for mobile Vosk applications
+
+Copyright © 2020 Alpha Cephei Inc
+
+%WER 28.63 [ 3442 / 12023, 497 ins, 919 del, 2026 sub ] exp/chain_a/tdnn/decode_test-podcast-wb/wer_10_0.0
+%WER 30.67 [ 3688 / 12023, 520 ins, 954 del, 2214 sub ] exp/chain_a/tdnn/decode_test-podcast-wb_l/wer_10_0.0
+%WER 26.68 [ 3208 / 12023, 464 ins, 910 del, 1834 sub ] exp/chain_a/tdnn/decode_test-podcast-wb_rescore/wer_10_0.0
+%WER 11.04 [ 7683 / 69600, 1592 ins, 925 del, 5166 sub ] exp/chain_a/tdnn/decode_test-wb/wer_10_0.5
+%WER 13.75 [ 9567 / 69600, 1896 ins, 1126 del, 6545 sub ] exp/chain_a/tdnn/decode_test-wb_l/wer_10_0.5
+%WER 9.02 [ 6279 / 69600, 1241 ins, 879 del, 4159 sub ] exp/chain_a/tdnn/decode_test-wb_rescore/wer_11_0.5
+
+Time taken 45.1052s: real-time factor assuming 100 frames/sec is 0.115468

app/src/main/assets/model-de/conf/mfcc.conf

@@ -0,0 +1,6 @@
+--use-energy=false
+--sample-frequency=16000
+--num-mel-bins=30
+--num-ceps=30
+--low-freq=100
+--high-freq=7600

app/src/main/assets/model-de/conf/model.conf

@@ -0,0 +1,10 @@
+--min-active=200
+--max-active=3000
+--beam=10.0
+--lattice-beam=2.0
+--acoustic-scale=1.0
+--frame-subsampling-factor=3
+--endpoint.silence-phones=1:2:3:4:5:6:7:8:9:10
+--endpoint.rule2.min-trailing-silence=0.5
+--endpoint.rule3.min-trailing-silence=1.0
+--endpoint.rule4.min-trailing-silence=2.0

app/src/main/assets/model-de/graph/disambig_tid.int

@@ -0,0 +1,7 @@
+14297
+14298
+14299
+14300
+14301
+14302
+14303

app/src/main/assets/model-de/graph/phones/word_boundary.int

@@ -0,0 +1,410 @@
+1 nonword
+2 begin
+3 end
+4 internal
+5 singleton
+6 nonword
+7 begin
+8 end
+9 internal
+10 singleton
+11 begin
+12 end
+13 internal
+14 singleton
+15 begin
+16 end
+17 internal
+18 singleton
+19 begin
+20 end
+21 internal
+22 singleton
+23 begin
+24 end
+25 internal
+26 singleton
+27 begin
+28 end
+29 internal
+30 singleton
+31 begin
+32 end
+33 internal
+34 singleton
+35 begin
+36 end
+37 internal
+38 singleton
+39 begin
+40 end
+41 internal
+42 singleton
+43 begin
+44 end
+45 internal
+46 singleton
+47 begin
+48 end
+49 internal
+50 singleton
+51 begin
+52 end
+53 internal
+54 singleton
+55 begin
+56 end
+57 internal
+58 singleton
+59 begin
+60 end
+61 internal
+62 singleton
+63 begin
+64 end
+65 internal
+66 singleton
+67 begin
+68 end
+69 internal
+70 singleton
+71 begin
+72 end
+73 internal
+74 singleton
+75 begin
+76 end
+77 internal
+78 singleton
+79 begin
+80 end
+81 internal
+82 singleton
+83 begin
+84 end
+85 internal
+86 singleton
+87 begin
+88 end
+89 internal
+90 singleton
+91 begin
+92 end
+93 internal
+94 singleton
+95 begin
+96 end
+97 internal
+98 singleton
+99 begin
+100 end
+101 internal
+102 singleton
+103 begin
+104 end
+105 internal
+106 singleton
+107 begin
+108 end
+109 internal
+110 singleton
+111 begin
+112 end
+113 internal
+114 singleton
+115 begin
+116 end
+117 internal
+118 singleton
+119 begin
+120 end
+121 internal
+122 singleton
+123 begin
+124 end
+125 internal
+126 singleton
+127 begin
+128 end
+129 internal
+130 singleton
+131 begin
+132 end
+133 internal
+134 singleton
+135 begin
+136 end
+137 internal
+138 singleton
+139 begin
+140 end
+141 internal
+142 singleton
+143 begin
+144 end
+145 internal
+146 singleton
+147 begin
+148 end
+149 internal
+150 singleton
+151 begin
+152 end
+153 internal
+154 singleton
+155 begin
+156 end
+157 internal
+158 singleton
+159 begin
+160 end
+161 internal
+162 singleton
+163 begin
+164 end
+165 internal
+166 singleton
+167 begin
+168 end
+169 internal
+170 singleton
+171 begin
+172 end
+173 internal
+174 singleton
+175 begin
+176 end
+177 internal
+178 singleton
+179 begin
+180 end
+181 internal
+182 singleton
+183 begin
+184 end
+185 internal
+186 singleton
+187 begin
+188 end
+189 internal
+190 singleton
+191 begin
+192 end
+193 internal
+194 singleton
+195 begin
+196 end
+197 internal
+198 singleton
+199 begin
+200 end
+201 internal
+202 singleton
+203 begin
+204 end
+205 internal
+206 singleton
+207 begin
+208 end
+209 internal
+210 singleton
+211 begin
+212 end
+213 internal
+214 singleton
+215 begin
+216 end
+217 internal
+218 singleton
+219 begin
+220 end
+221 internal
+222 singleton
+223 begin
+224 end
+225 internal
+226 singleton
+227 begin
+228 end
+229 internal
+230 singleton
+231 begin
+232 end
+233 internal
+234 singleton
+235 begin
+236 end
+237 internal
+238 singleton
+239 begin
+240 end
+241 internal
+242 singleton
+243 begin
+244 end
+245 internal
+246 singleton
+247 begin
+248 end
+249 internal
+250 singleton
+251 begin
+252 end
+253 internal
+254 singleton
+255 begin
+256 end
+257 internal
+258 singleton
+259 begin
+260 end
+261 internal
+262 singleton
+263 begin
+264 end
+265 internal
+266 singleton
+267 begin
+268 end
+269 internal
+270 singleton
+271 begin
+272 end
+273 internal
+274 singleton
+275 begin
+276 end
+277 internal
+278 singleton
+279 begin
+280 end
+281 internal
+282 singleton
+283 begin
+284 end
+285 internal
+286 singleton
+287 begin
+288 end
+289 internal
+290 singleton
+291 begin
+292 end
+293 internal
+294 singleton
+295 begin
+296 end
+297 internal
+298 singleton
+299 begin
+300 end
+301 internal
+302 singleton
+303 begin
+304 end
+305 internal
+306 singleton
+307 begin
+308 end
+309 internal
+310 singleton
+311 begin
+312 end
+313 internal
+314 singleton
+315 begin
+316 end
+317 internal
+318 singleton
+319 begin
+320 end
+321 internal
+322 singleton
+323 begin
+324 end
+325 internal
+326 singleton
+327 begin
+328 end
+329 internal
+330 singleton
+331 begin
+332 end
+333 internal
+334 singleton
+335 begin
+336 end
+337 internal
+338 singleton
+339 begin
+340 end
+341 internal
+342 singleton
+343 begin
+344 end
+345 internal
+346 singleton
+347 begin
+348 end
+349 internal
+350 singleton
+351 begin
+352 end
+353 internal
+354 singleton
+355 begin
+356 end
+357 internal
+358 singleton
+359 begin
+360 end
+361 internal
+362 singleton
+363 begin
+364 end
+365 internal
+366 singleton
+367 begin
+368 end
+369 internal
+370 singleton
+371 begin
+372 end
+373 internal
+374 singleton
+375 begin
+376 end
+377 internal
+378 singleton
+379 begin
+380 end
+381 internal
+382 singleton
+383 begin
+384 end
+385 internal
+386 singleton
+387 begin
+388 end
+389 internal
+390 singleton
+391 begin
+392 end
+393 internal
+394 singleton
+395 begin
+396 end
+397 internal
+398 singleton
+399 begin
+400 end
+401 internal
+402 singleton
+403 begin
+404 end
+405 internal
+406 singleton
+407 begin
+408 end
+409 internal
+410 singleton

app/src/main/assets/model-de/ivector/global_cmvn.stats

@@ -0,0 +1,3 @@
+ [
+  5.71762e+10 -1.787531e+09 4.831925e+08 4.409361e+09 -1.932859e+09 -1.543599e+09 -3.678115e+09 -3.702029e+09 -3.746038e+09 -1.137944e+09 -9.079639e+08 -5.819128e+07 -2.0947e+09 1.309573e+09 -5.171984e+08 2.481896e+08 -8.396431e+08 1.52164e+08 -6.130926e+08 1.542617e+07 -2.69509e+08 -2281178 -6.453142e+07 7354178 1.033131e+08 -1.133166e+07 6.952426e+07 -6.868613e+07 8611552 -7.709294e+07 6.473713e+08 
+  5.228252e+12 2.646175e+11 1.876415e+11 2.966005e+11 2.523884e+11 2.051858e+11 2.541094e+11 2.495341e+11 2.292826e+11 2.018152e+11 1.897722e+11 1.747636e+11 1.580083e+11 1.184324e+11 8.987214e+10 7.035342e+10 5.102559e+10 3.405446e+10 2.154957e+10 1.188595e+10 5.606266e+09 1.907599e+09 2.56771e+08 7.379798e+07 9.136799e+08 2.368205e+09 3.935658e+09 5.588645e+09 7.453864e+09 8.618391e+09 0 ]

app/src/main/assets/model-de/ivector/splice.conf

@@ -0,0 +1,2 @@
+--left-context=3
+--right-context=3

app/src/main/assets/model-de/uuid

@@ -0,0 +1 @@
+123

app/src/main/java/com/example/jarvis_stts/JarvisService.kt

@@ -0,0 +1,185 @@
+package com.example.jarvis_stts
+
+import android.app.NotificationChannel
+import android.app.NotificationManager
+import android.app.PendingIntent
+import android.app.Service
+import android.content.Intent
+import android.os.Build
+import android.os.IBinder
+import android.util.Log
+import androidx.core.app.NotificationCompat
+import org.vosk.Model
+import org.vosk.Recognizer
+import org.vosk.android.RecognitionListener
+import org.vosk.android.SpeechService
+import java.io.File
+import android.content.pm.ServiceInfo
+import org.json.JSONObject
+
+class JarvisService : Service(), RecognitionListener {
+
+    private var voskService: SpeechService? = null
+    private var voskModel: Model? = null
+    private var isInteracting = false
+
+    companion object {
+        const val CHANNEL_ID = "JarvisServiceChannel"
+        const val ACTION_START = "ACTION_START"
+        const val ACTION_PAUSE = "ACTION_PAUSE"
+        const val ACTION_RESUME = "ACTION_RESUME"
+    }
+
+    override fun onCreate() {
+        super.onCreate()
+        createNotificationChannel()
+
+        // Für Android 14 (API 34) und höher müssen wir den Typ beim Starten mitgeben
+        if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.UPSIDE_DOWN_CAKE) {
+            startForeground(
+                1,
+                createNotification("JARVIS hört zu..."),
+                ServiceInfo.FOREGROUND_SERVICE_TYPE_MICROPHONE
+            )
+        } else {
+            startForeground(1, createNotification("JARVIS hört zu..."))
+        }
+
+        initVosk()
+    }
+
+    override fun onStartCommand(intent: Intent?, flags: Int, startId: Int): Int {
+        when (intent?.action) {
+            ACTION_START -> resumeListening()
+            ACTION_PAUSE -> pauseListening()
+            ACTION_RESUME -> resumeListening()
+        }
+        return START_STICKY
+    }
+
+    private fun createNotificationChannel() {
+        if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.O) {
+            val channel = NotificationChannel(
+                CHANNEL_ID,
+                "JARVIS Background Service",
+                NotificationManager.IMPORTANCE_LOW
+            )
+            val manager = getSystemService(NotificationManager::class.java)
+            manager.createNotificationChannel(channel)
+        }
+    }
+
+    private fun createNotification(text: String): android.app.Notification {
+        val notificationIntent = Intent(this, MainActivity::class.java)
+        val pendingIntent = PendingIntent.getActivity(
+            this, 0, notificationIntent, PendingIntent.FLAG_IMMUTABLE
+        )
+
+        return NotificationCompat.Builder(this, CHANNEL_ID)
+            .setContentTitle("JARVIS ist aktiv")
+            .setContentText(text)
+            .setSmallIcon(android.R.drawable.ic_btn_speak_now) // Standard Android Icon
+            .setContentIntent(pendingIntent)
+            .setOngoing(true)
+            .build()
+    }
+
+    private fun updateNotification(text: String) {
+        val manager = getSystemService(NotificationManager::class.java)
+        manager.notify(1, createNotification(text))
+    }
+
+    private fun initVosk() {
+        val baseDir = getExternalFilesDir(null)
+        val modelFolder = File(baseDir, "model/model-de")
+
+        if (modelFolder.exists()) {
+            Log.d("JARVIS", "Modell gefunden unter: ${modelFolder.absolutePath}")
+            try {
+                // Wir laden das Modell und speichern es in der Klassen-Variable 'voskModel'
+                voskModel = Model(modelFolder.absolutePath)
+
+                Log.d("JARVIS", "Modell bereit, starte Hintergrund-Dienst...")
+
+                // Jetzt, wo das Modell da ist, können wir das Zuhören starten
+                resumeListening()
+
+            } catch (e: Exception) {
+                Log.e("JARVIS", "Vosk Fehler beim Modell-Laden: ${e.message}")
+                updateNotification("Fehler: Modell konnte nicht geladen werden")
+            }
+        } else {
+            Log.e("JARVIS", "ORDNER NICHT GEFUNDEN! Pfad: ${modelFolder.absolutePath}")
+            updateNotification("Fehler: Modell-Ordner fehlt")
+        }
+    }
+
+    private fun pauseListening() {
+        Log.d("JARVIS", "Service: Pausiere Zuhören")
+        voskService?.stop()
+        updateNotification("Pausiert (verarbeitet Anfrage...)")
+    }
+
+    private fun resumeListening() {
+        if (voskModel == null) return
+        Log.d("JARVIS", "Service: Starte Zuhören (Volles Wörterbuch)")
+        voskService?.stop()
+
+        // GANZ WICHTIG: Keine Grammar (Wortliste) mehr übergeben!
+        // Wir nutzen das volle deutsche Vokabular, um Fehlinterpretationen zu vermeiden.
+        val rec = Recognizer(voskModel, 16000.0f) 
+        
+        voskService = SpeechService(rec, 16000.0f)
+        voskService?.startListening(this)
+
+        isInteracting = false
+        updateNotification("Warte auf 'Jarvis'")
+    }
+
+    override fun onPartialResult(hypothesis: String) {
+        if (isInteracting) return
+
+        try {
+            val json = JSONObject(hypothesis)
+            val partialText = json.optString("partial").lowercase().trim()
+
+            // Wir ignorieren leere Strings und bekannte Rausch-Wörter für das Log
+            if (partialText.isNotEmpty() && partialText != "nun" && partialText.length > 2) {
+                Log.d("JARVIS_DEBUG", "Vosk hört: $partialText")
+            }
+
+            // Unser Regex-Check (den passen wir gleich an)
+            if (Regex("\\b(hey joe avis|hey gravis|bei gravis|hey joe|hey ich habe es|naja bis|welche avis|jarvis)\\b").containsMatchIn(partialText)) {
+                Log.d("JARVIS", "WAKE WORD ERKANNT: $partialText")
+                triggerJarvis()
+            }
+        } catch (e: Exception) {
+            Log.e("JARVIS", "Fehler beim Parsen: ${e.message}")
+        }
+    }
+
+    // onResult bleibt leer oder loggt nur zur Kontrolle
+    override fun onResult(hypothesis: String) {}
+
+    private fun triggerJarvis() {
+        isInteracting = true
+        pauseListening()
+        val intent = Intent(this, MainActivity::class.java).apply {
+            addFlags(Intent.FLAG_ACTIVITY_NEW_TASK or Intent.FLAG_ACTIVITY_SINGLE_TOP)
+            putExtra("WAKE_WORD_TRIGGERED", true)
+        }
+        startActivity(intent)
+    }
+
+    override fun onFinalResult(hypothesis: String) {}
+    override fun onError(e: Exception) { Log.e("JARVIS", "Service Error: ${e.message}") }
+    override fun onTimeout() {}
+
+    override fun onDestroy() {
+        super.onDestroy()
+        voskService?.stop()
+        voskService?.shutdown()
+    }
+
+    override fun onBind(intent: Intent?): IBinder? = null
+}

app/src/main/java/com/example/jarvis_stts/MainActivity.kt

@@ -3,9 +3,11 @@ package com.example.jarvis_stts
 import android.Manifest
 import android.content.Intent
 import android.content.pm.PackageManager
+import android.os.Build
 import android.os.Bundle
 import android.speech.RecognizerIntent
 import android.speech.tts.TextToSpeech
+import android.speech.tts.UtteranceProgressListener
 import android.speech.tts.Voice
 import android.util.Log
 import android.view.View
@@ -16,42 +18,58 @@ import androidx.core.app.ActivityCompat
 import androidx.core.content.ContextCompat
 import okhttp3.*
 import org.vosk.Model
-import org.vosk.Recognizer
-import org.vosk.android.RecognitionListener
-import org.vosk.android.SpeechService
 import org.vosk.android.StorageService
 import java.io.IOException
 import java.util.Locale
+import android.provider.Settings
+import android.net.Uri
 
-class MainActivity : AppCompatActivity(), RecognitionListener, TextToSpeech.OnInitListener {
+class MainActivity : AppCompatActivity(), TextToSpeech.OnInitListener {
 
-    // UI Elemente
     private lateinit var tvStatus: TextView
     private lateinit var etUrl: EditText
     private lateinit var spinnerVoices: Spinner
     private lateinit var tts: TextToSpeech
 
-    // Vosk & Netzwerk
-    private var voskService: SpeechService? = null
-    private var voskModel: Model? = null
     private val client = OkHttpClient()
     private var webSocket: WebSocket? = null
 
-    // TTS Stimmen
     private var availableVoices = mutableListOf<Voice>()
     private var voiceNames = mutableListOf<String>()
 
-    // Launcher für Google Spracherkennung
     private val speechRecognizerLauncher = registerForActivityResult(
         ActivityResultContracts.StartActivityForResult()
     ) { result ->
-        // Nach der Google-Eingabe starten wir Vosk wieder
-        startVosk() 
-
         if (result.resultCode == RESULT_OK && result.data != null) {
             val spokenText = result.data!!.getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS)?.get(0) ?: ""
             tvStatus.text = "Ich: $spokenText"
-            webSocket?.send(spokenText)
+            
+            if (webSocket != null) {
+                webSocket?.send(spokenText)
+                Log.d("JARVIS", "Sende an Server: $spokenText")
+            } else {
+                tvStatus.text = "Fehler: Nicht verbunden!"
+                // Falls nicht verbunden, Dienst wieder starten
+                tellServiceTo(JarvisService.ACTION_RESUME)
+            }
+        } else {
+            tellServiceTo(JarvisService.ACTION_RESUME)
+        }
+    }
+
+    private fun checkOverlayPermission() {
+        if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.M) {
+            if (!Settings.canDrawOverlays(this)) {
+                Log.d("JARVIS", "Overlay-Berechtigung fehlt. Öffne Einstellungen...")
+                val intent = Intent(
+                    Settings.ACTION_MANAGE_OVERLAY_PERMISSION,
+                    Uri.parse("package:$packageName")
+                )
+                // Wirft den Nutzer in die Einstellungen.
+                // Nach der Rückkehr muss die App meist neu gestartet/fokussiert werden.
+                startActivity(intent)
+                Toast.makeText(this, "Bitte erlaube JARVIS-AI, über anderen Apps zu erscheinen", Toast.LENGTH_LONG).show()
+            }
         }
     }
 
@@ -59,17 +77,22 @@ class MainActivity : AppCompatActivity(), RecognitionListener, TextToSpeech.OnIn
         super.onCreate(savedInstanceState)
         setContentView(R.layout.activity_main)
 
-        // 1. UI initialisieren
         tvStatus = findViewById(R.id.tvStatus)
         etUrl = findViewById(R.id.etUrl)
         spinnerVoices = findViewById(R.id.spinnerVoices)
         val btnConnect = findViewById<Button>(R.id.btnConnect)
         val btnSpeak = findViewById<Button>(R.id.btnSpeak)
+        val prefs = getSharedPreferences("JarvisPrefs", MODE_PRIVATE)
 
         tts = TextToSpeech(this, this)
+        val savedUrl = prefs.getString("server_url", "")
+        etUrl.setText(savedUrl)
+
+        // AUTOMATISCH VERBINDEN, falls eine URL gespeichert ist
+        if (!savedUrl.isNullOrEmpty()) {
+            connectToServer(savedUrl)
+        }
 
-        // 2. SharedPreferences
-        val prefs = getSharedPreferences("JarvisPrefs", MODE_PRIVATE)
         etUrl.setText(prefs.getString("server_url", ""))
 
         btnConnect.setOnClickListener {
@@ -80,66 +103,91 @@ class MainActivity : AppCompatActivity(), RecognitionListener, TextToSpeech.OnIn
             }
         }
 
-        btnSpeak.setOnClickListener { startVoiceInput() }
+        btnSpeak.setOnClickListener {
+            tellServiceTo(JarvisService.ACTION_PAUSE)
+            startVoiceInput()
+        }
 
-        // 3. Vosk Modell laden & Berechtigungen
+        checkPermissionsAndInit()
-        if (ContextCompat.checkSelfPermission(this, Manifest.permission.RECORD_AUDIO) != PackageManager.PERMISSION_GRANTED) {
+        checkOverlayPermission() // <-- Hier aufrufen!
-            ActivityCompat.requestPermissions(this, arrayOf(Manifest.permission.RECORD_AUDIO), 1)
+    }
+
+    // Wird aufgerufen, wenn die App im Hintergrund war und vom Service geweckt wird
+    override fun onNewIntent(intent: Intent?) {
+        super.onNewIntent(intent)
+        if (intent?.getBooleanExtra("WAKE_WORD_TRIGGERED", false) == true) {
+            Log.d("JARVIS", "MainActivity: Wake Word vom Service empfangen! Starte Google...")
+            // Kleiner Delay, damit die Audio-Hardware Zeit zum Umschalten hat
+            tvStatus.postDelayed({
+                startVoiceInput()
+            }, 500)
+        }
+    }
+
+    private fun checkPermissionsAndInit() {
+        val permissions = mutableListOf(Manifest.permission.RECORD_AUDIO)
+
+        // Notification Permission für Android 13+
+        if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.TIRAMISU) {
+            permissions.add(Manifest.permission.POST_NOTIFICATIONS)
+        }
+
+        val missingPermissions = permissions.filter {
+            ContextCompat.checkSelfPermission(this, it) != PackageManager.PERMISSION_GRANTED
+        }
+
+        if (missingPermissions.isNotEmpty()) {
+            ActivityCompat.requestPermissions(this, missingPermissions.toTypedArray(), 1)
         } else {
             initVoskModel()
         }
     }
 
+    override fun onRequestPermissionsResult(requestCode: Int, permissions: Array<out String>, grantResults: IntArray) {
+        super.onRequestPermissionsResult(requestCode, permissions, grantResults)
+        if (requestCode == 1 && grantResults.all { it == PackageManager.PERMISSION_GRANTED }) {
+            initVoskModel()
+        }
+    }
+
     private fun initVoskModel() {
         StorageService.unpack(this, "model-de", "model",
-            { model: Model ->
+            { _: Model ->
-                voskModel = model
+                Log.d("JARVIS", "Modell bereit, starte Hintergrund-Dienst...")
-                startVosk()
+                tellServiceTo(JarvisService.ACTION_START)
+                tvStatus.text = "Service läuft im Hintergrund!"
             },
-            { exception: IOException -> 
+            { exception: IOException ->
-                Log.e("JARVIS", "Vosk Fehler: ${exception.message}") 
+                Log.e("JARVIS", "Vosk Entpack-Fehler: ${exception.message}")
+                tvStatus.text = "Fehler: Modell nicht gefunden"
             }
         )
     }
 
-    private fun startVosk() {
+    private fun tellServiceTo(action: String) {
-        try {
+        val intent = Intent(this, JarvisService::class.java).apply {
-            if (voskModel == null) return
+            this.action = action
-            // Wir horchen auf "jarvis". [unk] lässt unbekannte Wörter zu.
+        }
-            val rec = Recognizer(voskModel, 16000.0f, "[\"computer\", \"[unk]\"]")
+        if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.O) {
-            //val rec = Recognizer(voskModel, 16000.0f, "[\"jarvis\", \"[unk]\"]")
+            startForegroundService(intent)
-            voskService = SpeechService(rec, 16000.0f)
+        } else {
-            voskService?.startListening(this)
+            startService(intent)
-            runOnUiThread { tvStatus.text = "Bereit (Warte auf 'Jarvis')" }
-        } catch (e: Exception) {
-            Log.e("JARVIS", "Vosk Start Fehler: ${e.message}")
         }
     }
 
-    // --- Vosk RecognitionListener ---
-    override fun onPartialResult(hypothesis: String) {
-        // Diese Zeile zeigt dir live im Logcat, was Vosk gerade verstanden hat:
-        Log.d("JARVIS", "Vosk hört: $hypothesis") 
-
-        // Testweise auf "computer" hören
-        if (hypothesis.contains("computer", ignoreCase = true)) {
-            voskService?.stop() 
-            startVoiceInput()
-        }
-    }
-
-    override fun onResult(hypothesis: String) {}
-    override fun onFinalResult(hypothesis: String) {}
-    override fun onError(e: Exception) { Log.e("JARVIS", "Vosk Error: ${e.message}") }
-    override fun onTimeout() {}
-
-    // --- Google STT & TTS ---
     private fun startVoiceInput() {
         val intent = Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH).apply {
             putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL, RecognizerIntent.LANGUAGE_MODEL_FREE_FORM)
             putExtra(RecognizerIntent.EXTRA_LANGUAGE, "de-DE")
+            putExtra(RecognizerIntent.EXTRA_PROMPT, "Ich höre dir zu...")
+            putExtra(RecognizerIntent.EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS, 2000L)
+            putExtra(RecognizerIntent.EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS, 2000L)
+        }
+        try {
+            speechRecognizerLauncher.launch(intent)
+        } catch (e: Exception) {
+            tellServiceTo(JarvisService.ACTION_RESUME)
         }
-        speechRecognizerLauncher.launch(intent)
     }
 
     private fun connectToServer(url: String) {
@@ -150,9 +198,15 @@ class MainActivity : AppCompatActivity(), RecognitionListener, TextToSpeech.OnIn
                 runOnUiThread { tvStatus.text = "Verbunden!" }
             }
             override fun onMessage(webSocket: WebSocket, text: String) {
-                runOnUiThread { tvStatus.text = "J.A.R.V.I.S.: $text" }
+                runOnUiThread { tvStatus.text = "JARVIS-AI: $text" }
                 speakOut(text)
             }
+            override fun onFailure(webSocket: WebSocket, t: Throwable, response: Response?) {
+                runOnUiThread {
+                    tvStatus.text = "Verbindungsfehler!"
+                    tellServiceTo(JarvisService.ACTION_RESUME)
+                }
+            }
         })
     }
 
@@ -160,6 +214,22 @@ class MainActivity : AppCompatActivity(), RecognitionListener, TextToSpeech.OnIn
         if (status == TextToSpeech.SUCCESS) {
             tts.language = Locale.GERMAN
             setupVoiceSpinner()
+
+            tts.setOnUtteranceProgressListener(object : UtteranceProgressListener() {
+                override fun onStart(utteranceId: String?) {}
+                override fun onDone(utteranceId: String?) {
+                    if (utteranceId == "TTS_DONE") {
+                        runOnUiThread {
+                            // Wenn Jarvis fertig gesprochen hat, lauschen wir wieder!
+                            tellServiceTo(JarvisService.ACTION_RESUME)
+                        }
+                    }
+                }
+                @Deprecated("Deprecated in Java")
+                override fun onError(utteranceId: String?) {
+                    runOnUiThread { tellServiceTo(JarvisService.ACTION_RESUME) }
+                }
+            })
         }
     }
 
@@ -184,14 +254,13 @@ class MainActivity : AppCompatActivity(), RecognitionListener, TextToSpeech.OnIn
     }
 
     private fun speakOut(text: String) {
-        tts.speak(text, TextToSpeech.QUEUE_FLUSH, null, "")
+        tts.speak(text, TextToSpeech.QUEUE_FLUSH, null, "TTS_DONE")
     }
 
     override fun onDestroy() {
-        voskService?.stop()
-        voskService?.shutdown()
         webSocket?.close(1000, "App Ende")
         tts.shutdown()
+        // Wir lassen den Service ABSICHTLICH nicht stoppen, wenn die Activity zerstört wird!
         super.onDestroy()
     }
 }

app/src/main/res/layout/activity_main.xml

@@ -48,6 +48,19 @@
         android:layout_marginVertical="8dp"
         android:background="#CCCCCC" />
 
+    <Button
+        android:id="@+id/btnSpeak"
+        android:layout_width="match_parent"
+        android:layout_height="wrap_content"
+        android:padding="20dp"
+        android:text="Sprechen" />
+
+    <View
+        android:layout_width="match_parent"
+        android:layout_height="1dp"
+        android:layout_marginVertical="8dp"
+        android:background="#CCCCCC" />
+
     <TextView
         android:id="@+id/tvStatus"
         android:layout_width="match_parent"
@@ -57,11 +70,4 @@
         android:text="Nicht verbunden"
         android:textSize="18sp" />
 
-    <Button
-        android:id="@+id/btnSpeak"
-        android:layout_width="match_parent"
-        android:layout_height="wrap_content"
-        android:padding="20dp"
-        android:text="Sprechen" />
-
 </LinearLayout>

settings.gradle.kts

@@ -23,5 +23,5 @@ dependencyResolutionManagement {
     }
 }
 
-rootProject.name = "jarvis-stts"
+rootProject.name = "jarvis-ai"
 include(":app")