diff --git a/lib/providers/voice_provider.dart b/lib/providers/voice_provider.dart
index 6c533b4..1887ae1 100644
--- a/lib/providers/voice_provider.dart
+++ b/lib/providers/voice_provider.dart
@@ -99,10 +99,23 @@ class VoiceNotifier extends Notifier<VoiceState> {
   StreamSubscription<Amplitude>? _amplitudeSubscription;
 
   // Recording / silence detection
+  //
+  // Silence threshold is dynamic: we track the session peak dBFS and treat
+  // "silent" as "current level is at least _dropFromPeakDb below peak."
+  // This auto-calibrates to whatever mic + room the user is on rather than
+  // assuming a fixed ambient level. Until the peak climbs above
+  // _dynamicArmDb we fall back to a conservative static threshold so a
+  // 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;
-  static const _silenceThresholdDb = -40.0;
-  static const _silenceDurationMs = 1500;
+  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
@@ -236,6 +249,7 @@ class VoiceNotifier extends Notifier<VoiceState> {
     if (!state.voiceModeActive) return;
 
     _silenceMs = 0;
+    _peakDb = -100.0;
     _recordingStartMs = DateTime.now().millisecondsSinceEpoch;
     state = state.copyWith(mode: VoiceMode.recording);
 
@@ -285,13 +299,22 @@ class VoiceNotifier extends Notifier<VoiceState> {
       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;
 
-    final isSilent = !validDb || db < _silenceThresholdDb;
+    // 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;