diff --git a/Libraries/LibMedia/CodedAudioFrameData.h b/Libraries/LibMedia/CodedAudioFrameData.h
new file mode 100644
index 0000000000..56c67d7934
--- /dev/null
+++ b/Libraries/LibMedia/CodedAudioFrameData.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (c) 2025, Gregory Bertilson <gregory@ladybird.org>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#pragma once
+
+namespace Media {
+
+class CodedAudioFrameData {
+public:
+    CodedAudioFrameData()
+    {
+    }
+};
+
+}
diff --git a/Libraries/LibMedia/CodedFrame.h b/Libraries/LibMedia/CodedFrame.h
index 361f633cdf..ed322a97cf 100644
--- a/Libraries/LibMedia/CodedFrame.h
+++ b/Libraries/LibMedia/CodedFrame.h
@@ -8,13 +8,14 @@
 
 #include <AK/ByteBuffer.h>
 #include <AK/Time.h>
+#include <LibMedia/CodedAudioFrameData.h>
 #include <LibMedia/CodedVideoFrameData.h>
 
 namespace Media {
 
 class CodedFrame final {
 public:
-    using AuxiliaryData = Variant<CodedVideoFrameData>;
+    using AuxiliaryData = Variant<CodedVideoFrameData, CodedAudioFrameData>;
 
     CodedFrame(AK::Duration timestamp, ByteBuffer&& data, AuxiliaryData auxiliary_data)
         : m_timestamp(timestamp)
diff --git a/Libraries/LibMedia/Containers/Matroska/MatroskaDemuxer.cpp b/Libraries/LibMedia/Containers/Matroska/MatroskaDemuxer.cpp
index de3e3dc39d..80e6a85492 100644
--- a/Libraries/LibMedia/Containers/Matroska/MatroskaDemuxer.cpp
+++ b/Libraries/LibMedia/Containers/Matroska/MatroskaDemuxer.cpp
@@ -190,9 +190,18 @@ DecoderErrorOr<CodedFrame> MatroskaDemuxer::get_next_sample_for_track(Track trac
         status.block = TRY(status.iterator.next_block());
         status.frame_index = 0;
     }
-    auto cicp = TRY(m_reader.track_for_track_number(track.identifier()))->video_track()->color_format.to_cicp();
+    auto aux_data = [&] -> CodedFrame::AuxiliaryData {
+        if (track.type() == TrackType::Video) {
+            auto cicp = MUST(m_reader.track_for_track_number(track.identifier()))->video_track()->color_format.to_cicp();
+            return CodedVideoFrameData(cicp);
+        }
+        if (track.type() == TrackType::Audio) {
+            return CodedAudioFrameData();
+        }
+        VERIFY_NOT_REACHED();
+    }();
     auto sample_data = DECODER_TRY_ALLOC(ByteBuffer::copy(status.block->frame(status.frame_index++)));
-    return CodedFrame(status.block->timestamp(), move(sample_data), CodedVideoFrameData(cicp));
+    return CodedFrame(status.block->timestamp(), move(sample_data), aux_data);
 }
 
 DecoderErrorOr<AK::Duration> MatroskaDemuxer::total_duration()
diff --git a/Libraries/LibMedia/FFmpeg/FFmpegDemuxer.cpp b/Libraries/LibMedia/FFmpeg/FFmpegDemuxer.cpp
index 9428016ecf..b42e2a2a01 100644
--- a/Libraries/LibMedia/FFmpeg/FFmpegDemuxer.cpp
+++ b/Libraries/LibMedia/FFmpeg/FFmpegDemuxer.cpp
@@ -181,18 +181,27 @@ DecoderErrorOr<CodedFrame> FFmpegDemuxer::get_next_sample_for_track(Track track)
             continue;
         }
 
-        auto color_primaries = static_cast<ColorPrimaries>(stream->codecpar->color_primaries);
-        auto transfer_characteristics = static_cast<TransferCharacteristics>(stream->codecpar->color_trc);
-        auto matrix_coefficients = static_cast<MatrixCoefficients>(stream->codecpar->color_space);
-        auto color_range = [stream] {
-            switch (stream->codecpar->color_range) {
-            case AVColorRange::AVCOL_RANGE_MPEG:
-                return VideoFullRangeFlag::Studio;
-            case AVColorRange::AVCOL_RANGE_JPEG:
-                return VideoFullRangeFlag::Full;
-            default:
-                return VideoFullRangeFlag::Unspecified;
+        auto auxiliary_data = [&]() -> CodedFrame::AuxiliaryData {
+            if (track.type() == TrackType::Video) {
+                auto color_primaries = static_cast<ColorPrimaries>(stream->codecpar->color_primaries);
+                auto transfer_characteristics = static_cast<TransferCharacteristics>(stream->codecpar->color_trc);
+                auto matrix_coefficients = static_cast<MatrixCoefficients>(stream->codecpar->color_space);
+                auto color_range = [stream] {
+                    switch (stream->codecpar->color_range) {
+                    case AVColorRange::AVCOL_RANGE_MPEG:
+                        return VideoFullRangeFlag::Studio;
+                    case AVColorRange::AVCOL_RANGE_JPEG:
+                        return VideoFullRangeFlag::Full;
+                    default:
+                        return VideoFullRangeFlag::Unspecified;
+                    }
+                }();
+                return CodedVideoFrameData(CodingIndependentCodePoints(color_primaries, transfer_characteristics, matrix_coefficients, color_range));
             }
+            if (track.type() == TrackType::Audio) {
+                return CodedAudioFrameData();
+            }
+            VERIFY_NOT_REACHED();
         }();
 
         // Copy the packet data so that we have a permanent reference to it whilst the Sample is alive, which allows us
@@ -202,7 +211,7 @@ DecoderErrorOr<CodedFrame> FFmpegDemuxer::get_next_sample_for_track(Track track)
         auto sample = CodedFrame(
             time_units_to_duration(m_packet->pts, stream->time_base),
             move(packet_data),
-            CodedVideoFrameData(CodingIndependentCodePoints(color_primaries, transfer_characteristics, matrix_coefficients, color_range)));
+            auxiliary_data);
 
         // Wipe the packet now that the data is safe.
         av_packet_unref(m_packet);