Add audio normalization option and support

Introduce an "audio_normalization" option across the app and implement normalization for audio-only downloads. Updates include: add config default (ConfigManager), new language strings, settings UI checkbox + help text and logic to auto-enable force-audio-format when normalization is enabled, and persist the setting. Pass the setting from main app to DownloadThread, and in the downloader force re-encoding to mp3 when necessary and append --postprocessor-args ExtractAudio:-af loudnorm=... to apply EBU R128 normalization. This ensures normalization works reliably (avoids ffmpeg stream-copy errors) and keeps the behavior scoped to ExtractAudio postprocessor.

ytsage/core/ytsage_downloader.py

@@ -72,6 +72,7 @@ class DownloadThread(QThread):
         preferred_output_format="mp4",
         force_audio_format=False,
         preferred_audio_format="best",
+        audio_normalization=False,
         filename_format=None,
     ) -> None:
         super().__init__()
@@ -100,6 +101,7 @@ class DownloadThread(QThread):
         self.preferred_output_format = preferred_output_format
         self.force_audio_format = force_audio_format
         self.preferred_audio_format = preferred_audio_format
+        self.audio_normalization = audio_normalization
         self.filename_format = filename_format
         self.paused: bool = False
         self.cancelled: bool = False
@@ -272,6 +274,22 @@ class DownloadThread(QThread):
             else:
                 logger.debug("Using --extract-audio with best quality (no conversion) for audio-only download")
                 
+        # Add Audio Normalization if enabled (only applies to audio-only downloads)
+        if self.audio_normalization and self.is_audio_only:
+            # Normalization using FFmpeg filters requires re-encoding the audio stream.
+            # If the user selected "Best (No conversion)", yt-dlp attempts to stream copy (-c:a copy),
+            # which will cause FFmpeg to crash with "Invalid argument".
+            # We fix this by forcing an explicit actual conversion (mp3) if no format was forced.
+            if not self.force_audio_format or self.preferred_audio_format == "best":
+                if "--extract-audio" not in cmd:
+                    cmd.append("--extract-audio")
+                cmd.extend(["--audio-format", "mp3"])
+                logger.debug("Forced audio format to mp3 since normalization requires re-encoding")
+
+            # Scope the argument specifically to ExtractAudio so it doesn't conflict with other PPs
+            cmd.extend(["--postprocessor-args", "ExtractAudio:-af loudnorm=I=-16:LRA=11:TP=-1.5"])
+            logger.debug("Added Audio Normalization (--postprocessor-args ExtractAudio:-af loudnorm=...)")
+
         # Output template with resolution in filename
         # Use string concatenation instead of Path.joinpath to avoid Path object issues
         base_path: str = self.path.as_posix()

ytsage/gui/ytsage_gui_dialogs/ytsage_dialogs_settings.py

@@ -261,12 +261,24 @@ class DownloadSettingsDialog(QDialog):
         # Load current audio format settings from ConfigManager
         self.force_audio_format_enabled = ConfigManager.get("force_audio_format") or False
         self.preferred_audio_format_value = ConfigManager.get("preferred_audio_format") or "best"
+        self.audio_normalization_enabled = ConfigManager.get("audio_normalization") or False
 
         # Enable/Disable force audio format checkbox
         self.force_audio_format_checkbox = QCheckBox(_("settings.force_audio_format"))
         self.force_audio_format_checkbox.setChecked(self.force_audio_format_enabled)
         audio_format_layout.addWidget(self.force_audio_format_checkbox)
 
+        # Enable/Disable audio normalization checkbox
+        self.audio_normalization_checkbox = QCheckBox(_("settings.audio_normalization", default="Audio Normalization"))
+        self.audio_normalization_checkbox.setChecked(self.audio_normalization_enabled)
+        audio_format_layout.addWidget(self.audio_normalization_checkbox)
+
+        # Audio normalization help text
+        audio_norm_help_label = QLabel(_("settings.audio_normalization_help", default="When enabled, audio will be normalized using EBU R128 standard."))
+        audio_norm_help_label.setWordWrap(True)
+        audio_norm_help_label.setStyleSheet("color: #cccccc; margin: 5px; font-size: 11px;")
+        audio_format_layout.addWidget(audio_norm_help_label)
+
         # Audio format selection layout
         audio_format_select_layout = QHBoxLayout()
         audio_format_label = QLabel(_("settings.preferred_audio_format"))
@@ -297,6 +309,10 @@ class DownloadSettingsDialog(QDialog):
         audio_help_label.setStyleSheet("color: #cccccc; margin: 5px; font-size: 11px;")
         audio_format_layout.addWidget(audio_help_label)
 
+        # Connect signals
+        self.audio_normalization_checkbox.stateChanged.connect(self._on_audio_normalization_toggled)
+        self.force_audio_format_checkbox.stateChanged.connect(self._on_force_audio_format_toggled)
+
         audio_format_group_box.setLayout(audio_format_layout)
         layout.addWidget(audio_format_group_box)
 
@@ -337,6 +353,22 @@ class DownloadSettingsDialog(QDialog):
         button_box.rejected.connect(self.reject)
         layout.addWidget(button_box)
 
+    def _on_audio_normalization_toggled(self, state: int) -> None:
+        """Handle logic when audio normalization is toggled."""
+        if state == Qt.CheckState.Checked.value:
+            # Normalization requires re-encoding, so we must force an audio format
+            self.force_audio_format_checkbox.setChecked(True)
+            
+            # If 'Best (No conversion)' is selected, change it to MP3 to ensure re-encoding
+            if self.audio_format_combo.currentIndex() == 0:
+                self.audio_format_combo.setCurrentIndex(2)  # Index 2 is typically MP3
+
+    def _on_force_audio_format_toggled(self, state: int) -> None:
+        """Handle logic when force audio format is toggled."""
+        if state == Qt.CheckState.Unchecked.value:
+            # If re-encoding is disabled, normalization cannot happen
+            self.audio_normalization_checkbox.setChecked(False)
+
     def browse_new_path(self) -> None:
         new_path = QFileDialog.getExistingDirectory(self, _("dialogs.select_folder"), str(self.current_path))
         if new_path:
@@ -385,6 +417,10 @@ class DownloadSettingsDialog(QDialog):
         audio_format_map = {0: "best", 1: "aac", 2: "mp3", 3: "flac", 4: "wav", 5: "opus", 6: "m4a", 7: "vorbis"}
         return audio_format_map.get(self.audio_format_combo.currentIndex(), "best")
 
+    def get_audio_normalization_enabled(self) -> bool:
+        """Returns whether audio normalization is enabled."""
+        return self.audio_normalization_checkbox.isChecked()
+
     def get_filename_format(self) -> str:
         """Returns the filename format string."""
         return self.filename_format_input.text().strip()
@@ -438,8 +474,10 @@ class DownloadSettingsDialog(QDialog):
             # Save audio format settings
             force_audio_format = self.get_force_audio_format_enabled()
             preferred_audio_format = self.get_preferred_audio_format()
+            audio_normalization = self.get_audio_normalization_enabled()
             ConfigManager.set("force_audio_format", force_audio_format)
             ConfigManager.set("preferred_audio_format", preferred_audio_format)
+            ConfigManager.set("audio_normalization", audio_normalization)
 
             # Save filename format
             filename_format = self.get_filename_format()

ytsage/gui/ytsage_gui_main.py

@@ -257,6 +257,7 @@ class YTSageApp(QMainWindow, FormatTableMixin, VideoInfoMixin, AnalysisMixin):
         self.preferred_output_format = ConfigManager.get("preferred_output_format") or "mp4"
         self.force_audio_format = ConfigManager.get("force_audio_format") or False
         self.preferred_audio_format = ConfigManager.get("preferred_audio_format") or "best"
+        self.audio_normalization = ConfigManager.get("audio_normalization") or False
         self.generic_mode_enabled = ConfigManager.get("generic_mode") or False
         # Track if video analysis is completed
         self.analysis_completed = False
@@ -640,12 +641,16 @@ class YTSageApp(QMainWindow, FormatTableMixin, VideoInfoMixin, AnalysisMixin):
             # Update Audio Format Settings
             new_force_audio_format = dialog.get_force_audio_format_enabled()
             new_preferred_audio_format = dialog.get_preferred_audio_format()
+            new_audio_normalization = dialog.get_audio_normalization_enabled()
             audio_format_changed = False
-            if new_force_audio_format != self.force_audio_format or new_preferred_audio_format != self.preferred_audio_format:
+            if (new_force_audio_format != self.force_audio_format or 
+                new_preferred_audio_format != self.preferred_audio_format or
+                new_audio_normalization != self.audio_normalization):
                 self.force_audio_format = new_force_audio_format
                 self.preferred_audio_format = new_preferred_audio_format
+                self.audio_normalization = new_audio_normalization
                 audio_format_changed = True
-                logger.info(f"Audio format settings updated - Force: {self.force_audio_format}, Preferred: {self.preferred_audio_format}")
+                logger.info(f"Audio format settings updated - Force: {self.force_audio_format}, Preferred: {self.preferred_audio_format}, Norm: {self.audio_normalization}")
 
             # Update Generic Mode Setting
             new_generic_mode = dialog.get_generic_mode_enabled()
@@ -778,6 +783,7 @@ class YTSageApp(QMainWindow, FormatTableMixin, VideoInfoMixin, AnalysisMixin):
             preferred_output_format=self.preferred_output_format,  # Pass preferred format
             force_audio_format=self.force_audio_format,  # Pass force audio format setting
             preferred_audio_format=self.preferred_audio_format,  # Pass preferred audio format
+            audio_normalization=self.audio_normalization,  # Pass audio normalization setting
             filename_format=filename_format,  # Pass the filename format
         )
 

ytsage/languages/en.json

@@ -327,6 +327,8 @@
     "format_mkv": "MKV (Feature-rich)",
     "audio_format_settings": "Audio Format Settings",
     "force_audio_format": "Force audio format for audio-only downloads",
+    "audio_normalization": "Audio Normalization (EBU R128)",
+    "audio_normalization_help": "When enabled, audio tracks will be normalized. Note: This requires re-encoding, so a specific audio format (like MP3 or M4A) must be forced.",
     "filename_format": "Output Filename Format",
     "filename_format_help": "Available variables: %(title)s, %(uploader)s, %(upload_date)s, %(resolution)s, %(id)s, %(ext)s. Standard yt-dlp output template syntax is supported.",
     "preferred_audio_format": "Preferred audio format:",

ytsage/utils/ytsage_config_manager.py

@@ -93,6 +93,7 @@ class ConfigManager:
         "preferred_output_format": "mp4",
         "force_audio_format": False,
         "preferred_audio_format": "best",
+        "audio_normalization": False,
         "filename_format": "%(title)s_%(resolution)s.%(ext)s",
         "cached_versions": {
             "ytdlp": {"version": None, "path": None, "last_check": 0, "path_mtime": 0},