feat: adds speech to text support

Co-authored-by: Rachit Gupta <[email protected]>
rchtgpt · Oct 15, 2023 · 494e83a · 494e83a
1 parent 7f434be
commit 494e83a
Show file tree

Hide file tree

Showing 7 changed files with 98 additions and 17 deletions.
diff --git a/android/app/src/main/AndroidManifest.xml b/android/app/src/main/AndroidManifest.xml
@@ -1,4 +1,6 @@
 <manifest xmlns:android="http://schemas.android.com/apk/res/android">
+    <uses-permission android:name="android.permission.RECORD_AUDIO"/>
+    <uses-permission android:name="android.permission.INTERNET"/>
     <application
         android:label="nl2ar"
         android:name="${applicationName}"

diff --git a/ios/Runner.xcodeproj/project.pbxproj b/ios/Runner.xcodeproj/project.pbxproj
@@ -215,7 +215,7 @@
 		97C146E61CF9000F007C117D /* Project object */ = {
 			isa = PBXProject;
 			attributes = {
-				LastUpgradeCheck = 1300;
+				LastUpgradeCheck = 1430;
 				ORGANIZATIONNAME = "";
 				TargetAttributes = {
 					331C8080294A63A400263BE5 = {

diff --git a/ios/Runner.xcodeproj/xcshareddata/xcschemes/Runner.xcscheme b/ios/Runner.xcodeproj/xcshareddata/xcschemes/Runner.xcscheme
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <Scheme
-   LastUpgradeVersion = "1300"
+   LastUpgradeVersion = "1430"
    version = "1.3">
    <BuildAction
       parallelizeBuildables = "YES"

diff --git a/ios/Runner/Info.plist b/ios/Runner/Info.plist
@@ -47,7 +47,15 @@
 	</array>
 	<key>UIViewControllerBasedStatusBarAppearance</key>
 	<false/>
+	<key>CADisableMinimumFrameDurationOnPhone</key>
+	<true/>
+	<key>UIApplicationSupportsIndirectInputEvents</key>
+	<true/>
+	<key>NSSpeechRecognitionUsageDescription</key>
+	<string>To display AR visualisations based on speech input</string>
+	<key>NSMicrophoneUsageDescription</key>
+	<string>To detect speech input</string>
 	<key>NSCameraUsageDescription</key>
-    <string>To capture profile photo please grant camera access</string>
+  <string>To capture profile photo please grant camera access</string>
 </dict>
 </plist>
diff --git a/lib/main.dart b/lib/main.dart
@@ -1,7 +1,9 @@
 import 'package:flutter/material.dart';
+import 'package:speech_to_text/speech_to_text.dart' as stt;
 import 'package:nl2ar/WebObjectsView.dart';
 
 void main() {
+  WidgetsFlutterBinding.ensureInitialized();
   runApp(const MyApp());
 }
 
@@ -32,16 +34,42 @@ class MyHomePage extends StatefulWidget {
 }
 
 class _MyHomePageState extends State<MyHomePage> {
-  int _counter = 0;
+  stt.SpeechToText _speech = stt.SpeechToText();
+  bool _isListening = false;
+  String _text = "This is text";
+  double _confidence = 1.0;
 
-  void _incrementCounter() {
-    setState(() {
-      _counter++;
-    });
+  @override
+  void initState() {
+    super.initState();
   }
 
   @override
   Widget build(BuildContext context) {
     return WebObjectsView();
   }
+
+  void _listen() async {
+    if (!_isListening) {
+      bool available = await _speech.initialize(
+        onStatus: (val) => print('onStatus: $val'),
+        onError: (val) => print('onError: $val'),
+      );
+      if (available) {
+        setState(() => _isListening = true);
+        _speech.listen(
+          onResult: (val) => setState(() {
+            _text = val.recognizedWords;
+            print(_text);
+            if (val.hasConfidenceRating && val.confidence > 0) {
+              _confidence = val.confidence;
+            }
+          }),
+        );
+      } else {
+        setState(() => _isListening = false);
+        _speech.stop();
+      }
+    }
+  }
 }
diff --git a/pubspec.lock b/pubspec.lock
@@ -45,10 +45,10 @@ packages:
     dependency: transitive
     description:
       name: collection
-      sha256: "4a07be6cb69c84d677a6c3096fcf960cc3285a8330b4603e0d463d15d9bd934c"
+      sha256: f092b211a4319e98e5ff58223576de6c2803db36221657b46c82574721240687
       url: "https://pub.dev"
     source: hosted
-    version: "1.17.1"
+    version: "1.17.2"
   crypto:
     dependency: transitive
     description:
@@ -172,18 +172,18 @@ packages:
     dependency: transitive
     description:
       name: matcher
-      sha256: "6501fbd55da300384b768785b83e5ce66991266cec21af89ab9ae7f5ce1c4cbb"
+      sha256: "1803e76e6653768d64ed8ff2e1e67bea3ad4b923eb5c56a295c3e634bad5960e"
       url: "https://pub.dev"
     source: hosted
-    version: "0.12.15"
+    version: "0.12.16"
   material_color_utilities:
     dependency: transitive
     description:
       name: material_color_utilities
-      sha256: d92141dc6fe1dad30722f9aa826c7fbc896d021d792f80678280601aff8cf724
+      sha256: "9528f2f296073ff54cb9fee677df673ace1218163c3bc7628093e7eed5203d41"
       url: "https://pub.dev"
     source: hosted
-    version: "0.2.0"
+    version: "0.5.0"
   meta:
     dependency: transitive
     description:
@@ -200,6 +200,14 @@ packages:
       url: "https://pub.dev"
     source: hosted
     version: "1.8.3"
+  pedantic:
+    dependency: transitive
+    description:
+      name: pedantic
+      sha256: "67fc27ed9639506c856c840ccce7594d0bdcd91bc8d53d6e52359449a1d50602"
+      url: "https://pub.dev"
+    source: hosted
+    version: "1.11.1"
   permission_handler:
     dependency: transitive
     description:
@@ -257,10 +265,34 @@ packages:
     dependency: transitive
     description:
       name: source_span
-      sha256: dd904f795d4b4f3b870833847c461801f6750a9fa8e61ea5ac53f9422b31f250
+      sha256: "53e943d4206a5e30df338fd4c6e7a077e02254531b138a15aec3bd143c1a8b3c"
       url: "https://pub.dev"
     source: hosted
-    version: "1.9.1"
+    version: "1.10.0"
+  speech_to_text:
+    dependency: "direct main"
+    description:
+      name: speech_to_text
+      sha256: "59393a58815a517dc1237a81ccbaf8302f44d107d84fafca9c295cdf7fff404f"
+      url: "https://pub.dev"
+    source: hosted
+    version: "6.3.0"
+  speech_to_text_macos:
+    dependency: transitive
+    description:
+      name: speech_to_text_macos
+      sha256: "6b5575e5a8346be1779838b0a482c259474965b5943668830b479147a75b5bfc"
+      url: "https://pub.dev"
+    source: hosted
+    version: "1.0.2"
+  speech_to_text_platform_interface:
+    dependency: transitive
+    description:
+      name: speech_to_text_platform_interface
+      sha256: "2ef9c0abf3b4340998fcb489afc4fc8cd7574eff21d912673be59b60ff16850c"
+      url: "https://pub.dev"
+    source: hosted
+    version: "2.1.0"
   stack_trace:
     dependency: transitive
     description:
@@ -297,9 +329,11 @@ packages:
     dependency: transitive
     description:
       name: test_api
-      sha256: eb6ac1540b26de412b3403a163d919ba86f6a973fe6cc50ae3541b80092fdcfb
+      sha256: "75760ffd7786fffdfb9597c35c5b27eaeec82be8edfb6d71d32651128ed7aab8"
       url: "https://pub.dev"
     source: hosted
+    version: "0.6.0"
+  vector_math:
     version: "0.5.1"
   typed_data:
     dependency: transitive
@@ -325,6 +359,14 @@ packages:
       url: "https://pub.dev"
     source: hosted
     version: "2.1.4"
+  web:
+    dependency: transitive
+    description:
+      name: web
+      sha256: dc8ccd225a2005c1be616fe02951e2e342092edf968cf0844220383757ef8f10
+      url: "https://pub.dev"
+    source: hosted
+    version: "0.1.4-beta"
 sdks:
   dart: ">=3.0.6 <4.0.0"
   flutter: ">=2.8.0"
diff --git a/pubspec.yaml b/pubspec.yaml
@@ -35,6 +35,7 @@ dependencies:
   # The following adds the Cupertino Icons font to your application.
   # Use with the CupertinoIcons class for iOS style icons.
   cupertino_icons: ^1.0.2
+  speech_to_text: ^6.3.0
   ar_flutter_plugin: ^0.7.3
   vector_math: ^2.1.4