1 files changed, 16 insertions, 1 deletions
diff --git a/src/audio/synth.cc b/src/audio/synth.cc
index 2072bb4..d66c502 100644
--- a/src/audio/synth.cc
+++ b/src/audio/synth.cc
@@ -30,6 +30,8 @@ struct Voice {
   int buffer_pos;
   float fractional_pos; // Fractional sample position for tempo scaling
 
+  int start_sample_offset; // Samples to wait before producing audio output
+
   const volatile float* active_spectral_data;
 };
 
@@ -152,7 +154,8 @@ void synth_commit_update(int spectrogram_id) {
       new_active_ptr, __ATOMIC_RELEASE);
 }
 
-void synth_trigger_voice(int spectrogram_id, float volume, float pan) {
+void synth_trigger_voice(int spectrogram_id, float volume, float pan,
+                         int start_offset_samples) {
   if (spectrogram_id < 0 || spectrogram_id >= MAX_SPECTROGRAMS ||
       !g_synth_data.spectrogram_registered[spectrogram_id]) {
 #if defined(DEBUG_LOG_SYNTH)
@@ -174,6 +177,11 @@ void synth_trigger_voice(int spectrogram_id, float volume, float pan) {
         pan, spectrogram_id);
     pan = (pan < -1.0f) ? -1.0f : 1.0f;
   }
+  if (start_offset_samples < 0) {
+    DEBUG_SYNTH("[SYNTH WARNING] Negative start_offset=%d, clamping to 0\n",
+                start_offset_samples);
+    start_offset_samples = 0;
+  }
 #endif
 
   for (int i = 0; i < MAX_VOICES; ++i) {
@@ -193,6 +201,7 @@ void synth_trigger_voice(int spectrogram_id, float volume, float pan) {
       v.buffer_pos = DCT_SIZE; // Force IDCT on first render
       v.fractional_pos =
           0.0f; // Initialize fractional position for tempo scaling
+      v.start_sample_offset = start_offset_samples; // NEW: Sample-accurate timing
       v.active_spectral_data =
           g_synth_data.active_spectrogram_data[spectrogram_id];
 
@@ -223,6 +232,12 @@ void synth_render(float* output_buffer, int num_frames) {
       if (!v.active)
         continue;
 
+      // NEW: Skip this sample if we haven't reached the trigger offset yet
+      if (v.start_sample_offset > 0) {
+        v.start_sample_offset--;
+        continue; // Don't produce audio until offset elapsed
+      }
+
       if (v.buffer_pos >= DCT_SIZE) {
         if (v.current_spectral_frame >= v.total_spectral_frames) {
           v.active = false;