diff --git a/pype/plugins/standalonepublisher/publish/collect_clip_instances.py b/pype/plugins/standalonepublisher/publish/collect_clip_instances.py
index a8603a50b4..f4d2810f2b 100644
--- a/pype/plugins/standalonepublisher/publish/collect_clip_instances.py
+++ b/pype/plugins/standalonepublisher/publish/collect_clip_instances.py
@@ -25,7 +25,8 @@ class CollectClipInstances(pyblish.api.InstancePlugin):
             "family": "audio",
             "families": ["ftrack"],
             "ftrackFamily": "audio",
-            "extension": ".wav"
+            "extension": ".wav",
+            "version": 1
         },
         "shotMain": {
             "family": "shot",
@@ -109,7 +110,7 @@ class CollectClipInstances(pyblish.api.InstancePlugin):
                     clip_in += self.timeline_frame_offset
                     clip_out += self.timeline_frame_offset
 
-                clip_duration = clip.duration().value - 1
+                clip_duration = clip.duration().value
                 self.log.info(f"clip duration: {clip_duration}")
 
                 source_in = clip.trimmed_range().start_time.value
@@ -126,7 +127,7 @@ class CollectClipInstances(pyblish.api.InstancePlugin):
                 else:
                     frame_start = clip_in
 
-                frame_end = frame_start + clip_duration
+                frame_end = frame_start + (clip_duration - 1)
 
                 # create shared new instance data
                 instance_data = {
diff --git a/pype/plugins/standalonepublisher/publish/extract_shot_data.py b/pype/plugins/standalonepublisher/publish/extract_shot_data.py
index 2732d0fa59..5b9fb43ffa 100644
--- a/pype/plugins/standalonepublisher/publish/extract_shot_data.py
+++ b/pype/plugins/standalonepublisher/publish/extract_shot_data.py
@@ -42,15 +42,31 @@ class ExtractShotData(pype.api.Extractor):
         # input_data = plib.ffprobe_streams(video_file_path)[0]
         # self.log.debug(f"__ input_data: `{input_data}`")
 
+        start = float(instance.data["clipInH"])
+        dur = float(instance.data["clipDurationH"])
+
+        if ext in ".wav":
+            start += 0.5
+            dur += 0.5
+
         args = [
             ffmpeg_path,
-            "-ss", str(instance.data["clipInH"] / fps),
+            "-ss", str(start / fps),
             "-i", video_file_path,
-            "-t", str(instance.data["clipDurationH"] / fps),
-            "-crf", "18",
-            "-pix_fmt", "yuv420p",
-            clip_trimed_path
+            "-t", str(dur / fps)
         ]
+        if ext in [".mov", ".mp4"]:
+            args.extend([
+                "-crf", "18",
+                "-pix_fmt", "yuv420p"])
+        elif ext in ".wav":
+            args.extend([
+                "-vn -acodec pcm_s16le",
+                "-ar 44100 -ac 2"])
+
+        # add output path
+        args.append(clip_trimed_path)
+
         self.log.info(f"Processing: {args}")
         ffmpeg_args = " ".join(args)
         output = pype.api.subprocess(ffmpeg_args)