diff --git a/facefusion/choices.py b/facefusion/choices.py
index 652dcb2..9571326 100755
--- a/facefusion/choices.py
+++ b/facefusion/choices.py
@@ -37,6 +37,7 @@ face_mask_regions : List[FaceMaskRegion] = list(face_mask_region_set.keys())
 
 audio_type_set : AudioTypeSet =\
 {
+	'm4a': 'audio/mp4',
 	'mp3': 'audio/mpeg',
 	'ogg': 'audio/ogg',
 	'wav': 'audio/x-wav'
@@ -52,6 +53,7 @@ image_type_set : ImageTypeSet =\
 video_type_set : VideoTypeSet =\
 {
 	'avi': 'video/x-msvideo',
+	'm4v': 'video/mp4',
 	'mkv': 'video/x-matroska',
 	'mp4': 'video/mp4',
 	'mov': 'video/quicktime',
diff --git a/facefusion/typing.py b/facefusion/typing.py
index 03e5483..0b59575 100755
--- a/facefusion/typing.py
+++ b/facefusion/typing.py
@@ -109,9 +109,9 @@ FaceMaskType = Literal['box', 'occlusion', 'region']
 FaceMaskRegion = Literal['skin', 'left-eyebrow', 'right-eyebrow', 'left-eye', 'right-eye', 'glasses', 'nose', 'mouth', 'upper-lip', 'lower-lip']
 FaceMaskRegionSet = Dict[FaceMaskRegion, int]
 
-AudioFormat = Literal['mp3', 'ogg', 'wav']
+AudioFormat = Literal['m4a', 'mp3', 'ogg', 'wav']
 ImageFormat = Literal['bmp', 'jpeg', 'png', 'tiff', 'webp']
-VideoFormat = Literal['avi', 'mkv', 'mov', 'mp4', 'webm']
+VideoFormat = Literal['avi', 'm4v', 'mkv', 'mov', 'mp4', 'webm']
 TempFrameFormat = Literal['bmp', 'jpeg', 'png', 'tiff']
 AudioTypeSet = Dict[AudioFormat, str]
 ImageTypeSet = Dict[ImageFormat, str]