Merge pull request 'Release v26.04.16.1 — Silero VAD voice detection' (#26) from dev into main

lib/providers/voice_provider.dart

@@ -8,6 +8,7 @@ import 'package:just_audio/just_audio.dart';
 import 'package:path_provider/path_provider.dart';
 import 'package:permission_handler/permission_handler.dart';
 import 'package:record/record.dart';
+import 'package:vad/vad.dart';
 
 import 'api_client_provider.dart';
 
@@ -98,25 +99,13 @@ class VoiceNotifier extends Notifier<VoiceState> {
   AudioPlayer? _player;
   StreamSubscription<Amplitude>? _amplitudeSubscription;
 
-  // Recording / silence detection
+  // VAD-based speech detection
-  //
+  VadHandler? _vadHandler;
-  // Silence threshold is dynamic: we track the session peak dBFS and treat
+  StreamSubscription<void>? _vadSpeechStartSub;
-  // "silent" as "current level is at least _dropFromPeakDb below peak."
+  StreamSubscription<List<double>>? _vadSpeechEndSub;
-  // This auto-calibrates to whatever mic + room the user is on rather than
+  bool _speechDetected = false;
-  // assuming a fixed ambient level. Until the peak climbs above
+  int _speechStartMs = 0;
-  // _dynamicArmDb we fall back to a conservative static threshold so a
+  static const _vadGraceMs = 1500;
-  // quiet room doesn't spin forever. A grace period at the start of the
-  // recording gives the user time to begin speaking before silence checks
-  // arm.
-  int _recordingStartMs = 0;
-  int _silenceMs = 0;
-  double _peakDb = -100.0;
-  static const _fallbackThresholdDb = -35.0;
-  static const _dropFromPeakDb = 15.0;
-  static const _dynamicArmDb = -20.0;
-  static const _graceMs = 1500;
-  static const _silenceDurationMs = 2000;
-  static const _minRecordingMs = 300;
 
   // Voice mode callbacks
   Future<void> Function(String transcript)? _onTranscript;
@@ -164,6 +153,9 @@ class VoiceNotifier extends Notifier<VoiceState> {
     required void Function(String message) onError,
   }) async {
     if (state.voiceModeActive) {
+      if (state.mode == VoiceMode.recording && !_speechDetected) {
+        onError('No speech detected');
+      }
       exitVoiceMode();
       return;
     }
@@ -211,12 +203,14 @@ class VoiceNotifier extends Notifier<VoiceState> {
     _amplitudeSubscription?.cancel();
     _amplitudeSubscription = null;
     _recorder?.stop();
+    _stopVad();
     _player?.stop();
     _ttsQueue.clear();
     _ttsPlaying = false;
     _sentenceBuffer = '';
     _lastSeenLength = 0;
     _streamComplete = false;
+    _speechDetected = false;
     _onTranscript = null;
     _onError = null;
     state = const VoiceState();
@@ -248,9 +242,8 @@ class VoiceNotifier extends Notifier<VoiceState> {
   Future<void> _startListening() async {
     if (!state.voiceModeActive) return;
 
-    _silenceMs = 0;
+    _speechDetected = false;
-    _peakDb = -100.0;
+    _speechStartMs = 0;
-    _recordingStartMs = DateTime.now().millisecondsSinceEpoch;
     state = state.copyWith(mode: VoiceMode.recording);
 
     final dir = _tempDir ?? await getTemporaryDirectory();
@@ -258,9 +251,6 @@ class VoiceNotifier extends Notifier<VoiceState> {
         '${dir.path}/voice_rec_${DateTime.now().millisecondsSinceEpoch}.m4a';
 
     try {
-      // Recreate the recorder each session — the record package can leave
-      // the native AudioRecord in a bad state after stop/error cycles,
-      // and a stale instance is the most common cause of "could not start".
       _recorder?.dispose();
       _recorder = AudioRecorder();
 
@@ -279,52 +269,52 @@ class VoiceNotifier extends Notifier<VoiceState> {
       _amplitudeSubscription = _recorder!
           .onAmplitudeChanged(const Duration(milliseconds: 200))
           .listen(_onAmplitude);
+
+      // VAD for speech detection — uses its own AudioRecorder internally
+      await _stopVad();
+      _vadHandler = VadHandler.create();
+      _vadSpeechStartSub = _vadHandler!.onSpeechStart.listen((_) {
+        if (!_speechDetected) {
+          _speechDetected = true;
+          _speechStartMs = DateTime.now().millisecondsSinceEpoch;
+        }
+      });
+      _vadSpeechEndSub = _vadHandler!.onSpeechEnd.listen((_) {
+        if (!state.voiceModeActive) return;
+        final now = DateTime.now().millisecondsSinceEpoch;
+        final sinceStart = _speechStartMs > 0 ? now - _speechStartMs : 0;
+        if (_speechDetected && sinceStart >= _vadGraceMs) {
+          _amplitudeSubscription?.cancel();
+          _amplitudeSubscription = null;
+          _stopVad();
+          _handleSilence();
+        }
+      });
+      await _vadHandler!.startListening(model: 'v5');
     } catch (e) {
       _onError?.call('Microphone error: $e');
       exitVoiceMode();
     }
   }
 
+  Future<void> _stopVad() async {
+    await _vadSpeechStartSub?.cancel();
+    _vadSpeechStartSub = null;
+    await _vadSpeechEndSub?.cancel();
+    _vadSpeechEndSub = null;
+    if (_vadHandler != null) {
+      await _vadHandler!.dispose();
+      _vadHandler = null;
+    }
+  }
+
   void _onAmplitude(Amplitude event) {
     if (!state.voiceModeActive) return;
-
     final db = event.current;
-    final validDb = !(db.isNaN || db.isInfinite);
+    if (db.isNaN || db.isInfinite) return;
-
+    final norm = ((db + 60.0) / 60.0).clamp(0.0, 1.0);
-    // Normalize dB to 0..1 for the pulse animation. -60dB is dead-quiet,
+    if ((norm - state.amplitude).abs() > 0.02) {
-    // 0dB is peak; we clamp and bias so the button visibly breathes even
+      state = state.copyWith(amplitude: norm);
-    // on soft speech without exploding on loud input.
-    if (validDb) {
-      final norm = ((db + 60.0) / 60.0).clamp(0.0, 1.0);
-      if ((norm - state.amplitude).abs() > 0.02) {
-        state = state.copyWith(amplitude: norm);
-      }
-      if (db > _peakDb) _peakDb = db;
-    }
-
-    final elapsed =
-        DateTime.now().millisecondsSinceEpoch - _recordingStartMs;
-    // Grace period at the start — let the user begin speaking before we
-    // start silence-counting. Also suppresses any false triggers while
-    // the native recorder is still warming up.
-    if (elapsed < _graceMs) return;
-    if (elapsed < _minRecordingMs) return;
-
-    // Dynamic threshold once we've seen real speech; static fallback
-    // before that so a dead-silent session doesn't spin forever.
-    final threshold =
-        _peakDb > _dynamicArmDb ? _peakDb - _dropFromPeakDb : _fallbackThresholdDb;
-    final isSilent = !validDb || db < threshold;
-
-    if (isSilent) {
-      _silenceMs += 200;
-      if (_silenceMs >= _silenceDurationMs) {
-        _amplitudeSubscription?.cancel();
-        _amplitudeSubscription = null;
-        _handleSilence();
-      }
-    } else {
-      _silenceMs = 0;
     }
   }
 

pubspec.lock

@@ -804,10 +804,10 @@ packages:
     dependency: "direct main"
     description:
       name: record
-      sha256: "2e3d56d196abcd69f1046339b75e5f3855b2406fc087e5991f6703f188aa03a6"
+      sha256: d5b6b334f3ab02460db6544e08583c942dbf23e3504bf1e14fd4cbe3d9409277
       url: "https://pub.dev"
     source: hosted
-    version: "5.2.1"
+    version: "6.2.0"
   record_android:
     dependency: transitive
     description:
@@ -816,22 +816,30 @@ packages:
       url: "https://pub.dev"
     source: hosted
     version: "1.5.1"
-  record_darwin:
+  record_ios:
     dependency: transitive
     description:
-      name: record_darwin
+      name: record_ios
-      sha256: e487eccb19d82a9a39cd0126945cfc47b9986e0df211734e2788c95e3f63c82c
+      sha256: "8df7c136131bd05efc19256af29b2ba6ccc000ccc2c80d4b6b6d7a8d21a3b5a9"
       url: "https://pub.dev"
     source: hosted
-    version: "1.2.2"
+    version: "1.2.0"
   record_linux:
-    dependency: "direct overridden"
+    dependency: transitive
     description:
       name: record_linux
       sha256: c31a35cc158cd666fc6395f7f56fc054f31685571684be6b97670a27649ce5c7
       url: "https://pub.dev"
     source: hosted
     version: "1.3.0"
+  record_macos:
+    dependency: transitive
+    description:
+      name: record_macos
+      sha256: "084902e63fc9c0c224c29203d6c75f0bdf9b6a40536c9d916393c8f4c4256488"
+      url: "https://pub.dev"
+    source: hosted
+    version: "1.2.1"
   record_platform_interface:
     dependency: transitive
     description:
@@ -1165,6 +1173,14 @@ packages:
       url: "https://pub.dev"
     source: hosted
     version: "4.5.3"
+  vad:
+    dependency: "direct main"
+    description:
+      name: vad
+      sha256: ef6c8b12c5af7a6a519ff5684f074b8a2ac00c434705f544af379ea77bccd258
+      url: "https://pub.dev"
+    source: hosted
+    version: "0.0.7+1"
   vector_math:
     dependency: transitive
     description:

pubspec.yaml

@@ -28,13 +28,11 @@ dependencies:
   google_fonts: ^8.0.2
   flutter_timezone: ^5.0.2
   url_launcher: ^6.3.1
-  record: ^5.0.0
+  record: ^6.2.0
+  vad: ^0.0.7
   just_audio: ^0.9.39
   table_calendar: ^3.1.2
 
-dependency_overrides:
-  record_linux: ^1.3.0
-
 dev_dependencies:
   flutter_test:
     sdk: flutter