rvsttd: hold-back last drain chunk for fade, same faded audio to Moonshine + WAV

This reverts commit 84474731e7.

Robovoice.App/AudioOutput.cs

@@ -8,7 +8,6 @@ internal sealed class AudioOutput : IDisposable
     private BufferedWaveProvider? _bufferProvider;
     private int _sampleRate;
     private string _deviceName = string.Empty;
-    private float _lastSample;
     private bool _disposed;
 
     public Action<string>? Log { get; set; }
@@ -19,7 +18,6 @@ internal sealed class AudioOutput : IDisposable
 
         _sampleRate = sampleRate;
         _deviceName = deviceName ?? string.Empty;
-        _lastSample = 0f;
 
         Stop();
 
@@ -44,9 +42,6 @@ internal sealed class AudioOutput : IDisposable
         ObjectDisposedException.ThrowIf(_disposed, this);
         if (_bufferProvider is null) return;
 
-        if (samples.Length > 0)
-            _lastSample = samples[^1];
-
         byte[] bytes = new byte[samples.Length * sizeof(float)];
         Buffer.BlockCopy(samples, 0, bytes, 0, bytes.Length);
         _bufferProvider.AddSamples(bytes, 0, bytes.Length);
@@ -57,21 +52,8 @@ internal sealed class AudioOutput : IDisposable
         ObjectDisposedException.ThrowIf(_disposed, this);
         if (_bufferProvider is null || _sampleRate == 0) return;
 
-        // Fade out from last sample to zero over 5ms to avoid click
-        int fadeSamples = (int)(_sampleRate * 0.005);
-        float[] fade = new float[fadeSamples];
-        for (int i = 0; i < fadeSamples; i++)
-        {
-            float t = (float)i / fadeSamples;
-            fade[i] = _lastSample * (1f - t);
-        }
-        WriteSamples(fade);
-
-        // Then 500ms of silence to let NAudio drain
         int padSamples = (int)(_sampleRate * 0.5);
         WriteSamples(new float[padSamples]);
-        
-        _lastSample = 0f;
     }
 
     private void OnPlaybackStopped(object? sender, StoppedEventArgs e)
@@ -89,7 +71,6 @@ internal sealed class AudioOutput : IDisposable
         }
         _bufferProvider?.ClearBuffer();
         _bufferProvider = null;
-        _lastSample = 0f;
     }
 
     private static int FindDevice(string? deviceName)

rvsttd/src/main.rs

@@ -324,27 +324,55 @@ fn transcriber_loop(
     // Drain trailing audio from ALSA buffer (cpal stream still alive).
     // Fixed 100ms window — cpal delivers every ~50ms (800 samples @ 16kHz),
     // so this captures 1-2 more callbacks worth of trailing audio.
+    // Hold one chunk back so we can apply a fade-out to the very last one.
     let drain_deadline = std::time::Instant::now() + Duration::from_millis(100);
+    let mut held_chunk: Option<Vec<f32>> = None;
     while std::time::Instant::now() < drain_deadline {
         match rx.recv_timeout(drain_deadline - std::time::Instant::now()) {
             Ok(chunk) => {
-                if let Some(ref mut r) = recorder {
-                    r.add_audio(&chunk);
-                }
-
-                unsafe {
-                    moonshine_transcribe_add_audio_to_stream(
-                        handle, stream_handle,
-                        chunk.as_ptr(), chunk.len() as u64,
-                        SAMPLE_RATE, 0,
-                    );
+                // Feed previously held chunk to Moonshine + recorder (no fade)
+                if let Some(prev) = held_chunk.take() {
+                    if let Some(ref mut r) = recorder {
+                        r.add_audio(&prev);
+                    }
+                    unsafe {
+                        moonshine_transcribe_add_audio_to_stream(
+                            handle, stream_handle,
+                            prev.as_ptr(), prev.len() as u64,
+                            SAMPLE_RATE, 0,
+                        );
+                    }
                 }
+                held_chunk = Some(chunk);
             }
             Err(mpsc::RecvTimeoutError::Timeout) => break,
             Err(mpsc::RecvTimeoutError::Disconnected) => break,
         }
     }
 
+    // Apply 5ms fade-out to the last chunk, then feed to both Moonshine and recorder
+    if let Some(mut chunk) = held_chunk.take() {
+        let fade_samples = (SAMPLE_RATE as usize * 5) / 1000;
+        if chunk.len() > fade_samples {
+            let start = chunk.len() - fade_samples;
+            for i in 0..fade_samples {
+                let t = 1.0 - (i as f32 / fade_samples as f32);
+                chunk[start + i] *= t;
+            }
+        }
+
+        if let Some(ref mut r) = recorder {
+            r.add_audio(&chunk);
+        }
+        unsafe {
+            moonshine_transcribe_add_audio_to_stream(
+                handle, stream_handle,
+                chunk.as_ptr(), chunk.len() as u64,
+                SAMPLE_RATE, 0,
+            );
+        }
+    }
+
     // If aborted (new session took over), skip final flush entirely
     if aborted.load(Ordering::SeqCst) {
         unsafe { moonshine_stop_stream(handle, stream_handle) };