fix: try smoothing playback

speech_to_text.py

@@ -240,13 +240,31 @@ class SpeechToText:
                 )
                 print(f"Using device default sample rate: {device_info['defaultSampleRate']}")
             
-            # Play the audio
+            # Play the audio with larger buffer for smoother playback
-            chunk_size = 1024
+            # Using larger chunk size and adding a small delay to allow the buffer to fill
-            data = wf.readframes(chunk_size)
+            chunk_size = 8192  # Increased from 1024 to reduce stuttering
             
-            while len(data) > 0:
+            # Pre-buffer data for smoother playback
-                output_stream.write(data)
+            audio_data = []
+            while True:
                 data = wf.readframes(chunk_size)
+                if len(data) == 0:
+                    break
+                audio_data.append(data)
+            
+            # Reset file position for playback
+            wf.rewind()
+            
+            # Set a larger buffer size for output
+            buffer_size = chunk_size * 4
+            
+            print(f"Playing audio with buffer size {buffer_size} bytes")
+            
+            # Play the buffered data with lower CPU load
+            for data in audio_data:
+                output_stream.write(data)
+                # Small sleep to reduce CPU load and allow buffer to process
+                time.sleep(0.005)
             
             # Clean up resources
             output_stream.stop_stream()