diff --git a/votify/api/proto/audio_files_extension.proto b/votify/api/proto/audio_files_extension.proto
new file mode 100644
index 0000000..d5c521f
--- /dev/null
+++ b/votify/api/proto/audio_files_extension.proto
@@ -0,0 +1,25 @@
+syntax = "proto3";
+
+package votify.extendedmetadata.audiofiles;
+
+import "votify/api/proto/extendedmetadata.proto";
+
+message NormalizationParams {
+    float loudness_db = 1;
+    float true_peak_db = 2;
+}
+
+message ExtendedAudioFile {
+    reserved 2;
+    reserved 3;
+
+    votify.extendedmetadata.AudioFile file = 1;
+    int32 average_bitrate = 4;
+}
+
+message AudioFilesExtensionResponse {
+    repeated ExtendedAudioFile files = 1;
+    NormalizationParams default_file_normalization_params = 2;
+    NormalizationParams default_album_normalization_params = 3;
+    bytes audio_id = 4;
+}
diff --git a/votify/api/proto/audio_files_extension_pb2.py b/votify/api/proto/audio_files_extension_pb2.py
new file mode 100644
index 0000000..98b01d5
--- /dev/null
+++ b/votify/api/proto/audio_files_extension_pb2.py
@@ -0,0 +1,41 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# NO CHECKED-IN PROTOBUF GENCODE
+# source: votify/api/proto/audio_files_extension.proto
+# Protobuf Python Version: 6.33.4
+"""Generated protocol buffer code."""
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import runtime_version as _runtime_version
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+_runtime_version.ValidateProtobufRuntimeVersion(
+    _runtime_version.Domain.PUBLIC,
+    6,
+    33,
+    4,
+    '',
+    'votify/api/proto/audio_files_extension.proto'
+)
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+from votify.api.proto import extendedmetadata_pb2 as votify_dot_api_dot_proto_dot_extendedmetadata__pb2
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n,votify/api/proto/audio_files_extension.proto\x12\"votify.extendedmetadata.audiofiles\x1a\'votify/api/proto/extendedmetadata.proto\"@\n\x13NormalizationParams\x12\x13\n\x0bloudness_db\x18\x01 \x01(\x02\x12\x14\n\x0ctrue_peak_db\x18\x02 \x01(\x02\"j\n\x11\x45xtendedAudioFile\x12\x30\n\x04\x66ile\x18\x01 \x01(\x0b\x32\".votify.extendedmetadata.AudioFile\x12\x17\n\x0f\x61verage_bitrate\x18\x04 \x01(\x05J\x04\x08\x02\x10\x03J\x04\x08\x03\x10\x04\"\xbe\x02\n\x1b\x41udioFilesExtensionResponse\x12\x44\n\x05\x66iles\x18\x01 \x03(\x0b\x32\x35.votify.extendedmetadata.audiofiles.ExtendedAudioFile\x12\x62\n!default_file_normalization_params\x18\x02 \x01(\x0b\x32\x37.votify.extendedmetadata.audiofiles.NormalizationParams\x12\x63\n\"default_album_normalization_params\x18\x03 \x01(\x0b\x32\x37.votify.extendedmetadata.audiofiles.NormalizationParams\x12\x10\n\x08\x61udio_id\x18\x04 \x01(\x0c\x62\x06proto3')
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'votify.api.proto.audio_files_extension_pb2', _globals)
+if not _descriptor._USE_C_DESCRIPTORS:
+  DESCRIPTOR._loaded_options = None
+  _globals['_NORMALIZATIONPARAMS']._serialized_start=125
+  _globals['_NORMALIZATIONPARAMS']._serialized_end=189
+  _globals['_EXTENDEDAUDIOFILE']._serialized_start=191
+  _globals['_EXTENDEDAUDIOFILE']._serialized_end=297
+  _globals['_AUDIOFILESEXTENSIONRESPONSE']._serialized_start=300
+  _globals['_AUDIOFILESEXTENSIONRESPONSE']._serialized_end=618
+# @@protoc_insertion_point(module_scope)
diff --git a/votify/api/proto/audio_files_extension_pb2.pyi b/votify/api/proto/audio_files_extension_pb2.pyi
new file mode 100644
index 0000000..638b23a
--- /dev/null
+++ b/votify/api/proto/audio_files_extension_pb2.pyi
@@ -0,0 +1,36 @@
+from votify.api.proto import extendedmetadata_pb2 as _extendedmetadata_pb2
+from google.protobuf.internal import containers as _containers
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import message as _message
+from collections.abc import Iterable as _Iterable, Mapping as _Mapping
+from typing import ClassVar as _ClassVar, Optional as _Optional, Union as _Union
+
+DESCRIPTOR: _descriptor.FileDescriptor
+
+class NormalizationParams(_message.Message):
+    __slots__ = ("loudness_db", "true_peak_db")
+    LOUDNESS_DB_FIELD_NUMBER: _ClassVar[int]
+    TRUE_PEAK_DB_FIELD_NUMBER: _ClassVar[int]
+    loudness_db: float
+    true_peak_db: float
+    def __init__(self, loudness_db: _Optional[float] = ..., true_peak_db: _Optional[float] = ...) -> None: ...
+
+class ExtendedAudioFile(_message.Message):
+    __slots__ = ("file", "average_bitrate")
+    FILE_FIELD_NUMBER: _ClassVar[int]
+    AVERAGE_BITRATE_FIELD_NUMBER: _ClassVar[int]
+    file: _extendedmetadata_pb2.AudioFile
+    average_bitrate: int
+    def __init__(self, file: _Optional[_Union[_extendedmetadata_pb2.AudioFile, _Mapping]] = ..., average_bitrate: _Optional[int] = ...) -> None: ...
+
+class AudioFilesExtensionResponse(_message.Message):
+    __slots__ = ("files", "default_file_normalization_params", "default_album_normalization_params", "audio_id")
+    FILES_FIELD_NUMBER: _ClassVar[int]
+    DEFAULT_FILE_NORMALIZATION_PARAMS_FIELD_NUMBER: _ClassVar[int]
+    DEFAULT_ALBUM_NORMALIZATION_PARAMS_FIELD_NUMBER: _ClassVar[int]
+    AUDIO_ID_FIELD_NUMBER: _ClassVar[int]
+    files: _containers.RepeatedCompositeFieldContainer[ExtendedAudioFile]
+    default_file_normalization_params: NormalizationParams
+    default_album_normalization_params: NormalizationParams
+    audio_id: bytes
+    def __init__(self, files: _Optional[_Iterable[_Union[ExtendedAudioFile, _Mapping]]] = ..., default_file_normalization_params: _Optional[_Union[NormalizationParams, _Mapping]] = ..., default_album_normalization_params: _Optional[_Union[NormalizationParams, _Mapping]] = ..., audio_id: _Optional[bytes] = ...) -> None: ...