diff --git a/audio_splitter/ffmpeg.py b/audio_splitter/ffmpeg.py
index b5119b4..4471f58 100644
--- a/audio_splitter/ffmpeg.py
+++ b/audio_splitter/ffmpeg.py
@@ -269,6 +269,109 @@ def extract_cover_image(input_file: str, output_path: str) -> bool:
     return True
 
 
+def _build_inputs(cmd: List[str], input_file: str, cover_image_path: Optional[str]) -> None:
+    """Add input files to the command."""
+    if cover_image_path:
+        cmd.extend(['-i', cover_image_path])
+    cmd.extend(['-i', input_file])
+
+
+def _build_time_options(cmd: List[str], start_seconds: int, duration_seconds: int) -> None:
+    """Add time-based options to the command."""
+    cmd.extend(['-ss', format_time(start_seconds), '-t', format_time(duration_seconds)])
+
+
+def _build_metadata(cmd: List[str], metadata: Optional[Dict]) -> None:
+    """Add metadata options to the command."""
+    cmd.append('-map_metadata')
+    cmd.append('-1')
+    if metadata:
+        for key, value in metadata.items():
+            if value is not None and value != '':
+                cmd.extend(['-metadata', f"{key}={value}"])
+
+
+def _build_cover_image_mapping(
+    cmd: List[str],
+    audio_codec: Optional[str],
+    video_codec: Optional[str],
+    video_quality: Optional[int],
+) -> None:
+    """Build stream mapping for cover image extraction (audio + cover video)."""
+    cmd.extend(['-map', '1:a:0', '-map', '0:v:0'])
+
+    if video_codec and video_codec != 'copy':
+        cmd.extend(['-c:v', video_codec])
+    else:
+        cmd.extend(['-c:v', 'png'])
+
+    if audio_codec and audio_codec != 'copy':
+        cmd.extend(['-c:a', audio_codec])
+    else:
+        cmd.extend(['-c:a', 'copy'])
+
+    cmd.append('-sn')
+
+    if video_quality is not None:
+        cmd.extend(['-q:v', str(video_quality)])
+
+
+def _build_standard_mapping(
+    cmd: List[str],
+    stream_info: Dict,
+    audio_codec: Optional[str],
+    video_codec: Optional[str],
+    subtitle_codec: Optional[str],
+    video_quality: Optional[int],
+    drop_video: bool,
+    drop_subs: bool,
+) -> None:
+    """Build stream mapping for standard extraction (no cover image)."""
+    if drop_video and drop_subs:
+        cmd.extend(['-map', '0:a:0'])
+    elif drop_video:
+        cmd.extend(['-map', '0:a:0', '-map', '0:s?'])
+    elif drop_subs:
+        cmd.extend(['-map', '0:a:0', '-map', '0:v:0'])
+    else:
+        cmd.extend(['-map', '0'])
+
+    if audio_codec and audio_codec != 'copy':
+        cmd.extend(['-c:a', audio_codec])
+    else:
+        cmd.extend(['-c:a', 'copy'])
+
+    if not drop_video and stream_info.get('has_video'):
+        if video_codec and video_codec != 'copy':
+            cmd.extend(['-c:v', video_codec])
+            if video_quality is not None:
+                cmd.extend(['-q:v', str(video_quality)])
+        else:
+            cmd.extend(['-c:v', 'copy'])
+    else:
+        cmd.append('-vn')
+
+    if not drop_subs and stream_info.get('has_subtitle'):
+        if subtitle_codec and subtitle_codec != 'copy':
+            cmd.extend(['-c:s', subtitle_codec])
+        else:
+            cmd.extend(['-c:s', 'copy'])
+    else:
+        cmd.append('-sn')
+
+
+def _build_format(cmd: List[str], format_opt: Optional[str]) -> None:
+    """Add output format option if specified."""
+    if format_opt:
+        ffmpeg_format = FORMAT_INFO.get(format_opt, {}).get('ffmpeg', format_opt)
+        cmd.extend(['-f', ffmpeg_format])
+
+
+def _build_output(cmd: List[str], output_path: str) -> None:
+    """Add output file to the command."""
+    cmd.extend(['-y', output_path])
+
+
 def build_ffmpeg_command(
     input_file: str,
     start_seconds: int,
@@ -309,93 +412,21 @@ def build_ffmpeg_command(
     """
     cmd = ['ffmpeg']
 
-    # Add cover image as first input if provided
+    _build_inputs(cmd, input_file, cover_image_path)
+    _build_time_options(cmd, start_seconds, duration_seconds)
+    _build_metadata(cmd, metadata)
+
     if cover_image_path:
-        cmd.extend(['-i', cover_image_path])
-
-    # Add main input file
-    cmd.extend(['-i', input_file])
-
-    # Time options
-    cmd.extend(['-ss', format_time(start_seconds), '-t', format_time(duration_seconds)])
-
-    # Clear all original metadata.
-    cmd.append('-map_metadata')
-    cmd.append('-1')
-
-    # Apply custom metadata.
-    if metadata:
-        for key, value in metadata.items():
-            if value is not None and value != '':
-                cmd.extend(['-metadata', f"{key}={value}"])
-
-    # ---------- Stream mapping and codecs ----------
-    if cover_image_path:
-        # We have two inputs: index 0 = cover image, index 1 = main input
-        # Map audio from main input (index 1) and video from cover image (index 0)
-        cmd.extend(['-map', '1:a:0', '-map', '0:v:0'])
-
-        # Video codec: use user-specified codec if provided, otherwise fallback to png
-        if video_codec and video_codec != 'copy':
-            cmd.extend(['-c:v', video_codec])
-        else:
-            cmd.extend(['-c:v', 'png'])
-
-        # Audio codec
-        if audio_codec and audio_codec != 'copy':
-            cmd.extend(['-c:a', audio_codec])
-        else:
-            cmd.extend(['-c:a', 'copy'])
-
-        # Subtitle: we don't copy subtitles when using cover image (they would be from main input)
-        cmd.append('-sn')
-
-        # Video quality if specified
-        if video_quality is not None:
-            cmd.extend(['-q:v', str(video_quality)])
-
+        _build_cover_image_mapping(cmd, audio_codec, video_codec, video_quality)
     else:
-        # Standard mapping (no cover image)
-        if drop_video and drop_subs:
-            cmd.extend(['-map', '0:a:0'])
-        elif drop_video:
-            cmd.extend(['-map', '0:a:0', '-map', '0:s?'])
-        elif drop_subs:
-            cmd.extend(['-map', '0:a:0', '-map', '0:v:0'])
-        else:
-            cmd.extend(['-map', '0'])
+        _build_standard_mapping(
+            cmd, stream_info, audio_codec, video_codec, subtitle_codec,
+            video_quality, drop_video, drop_subs
+        )
 
-        # Audio codec
-        if audio_codec and audio_codec != 'copy':
-            cmd.extend(['-c:a', audio_codec])
-        else:
-            cmd.extend(['-c:a', 'copy'])
+    _build_format(cmd, format_opt)
+    _build_output(cmd, output_path)
 
-        # Video codec
-        if not drop_video and stream_info.get('has_video'):
-            if video_codec and video_codec != 'copy':
-                cmd.extend(['-c:v', video_codec])
-                # Add video quality if specified (only when re-encoding)
-                if video_quality is not None:
-                    cmd.extend(['-q:v', str(video_quality)])
-            else:
-                cmd.extend(['-c:v', 'copy'])
-        else:
-            cmd.append('-vn')
-
-        # Subtitle codec
-        if not drop_subs and stream_info.get('has_subtitle'):
-            if subtitle_codec and subtitle_codec != 'copy':
-                cmd.extend(['-c:s', subtitle_codec])
-            else:
-                cmd.extend(['-c:s', 'copy'])
-        else:
-            cmd.append('-sn')
-
-    # Output format
-    if format_opt:
-        ffmpeg_format = FORMAT_INFO.get(format_opt, {}).get('ffmpeg', format_opt)
-        cmd.extend(['-f', ffmpeg_format])
-
-    cmd.extend(['-y', output_path])
     return cmd
+
+