diff --git a/video/cloud-client/analyze/beta_snippets.py b/video/cloud-client/analyze/beta_snippets.py
index ada4f9b4eb4..78ee469e077 100644
--- a/video/cloud-client/analyze/beta_snippets.py
+++ b/video/cloud-client/analyze/beta_snippets.py
@@ -35,7 +35,8 @@ def speech_transcription(input_uri):
     features = [videointelligence.enums.Feature.SPEECH_TRANSCRIPTION]
 
     config = videointelligence.types.SpeechTranscriptionConfig(
-        language_code='en-US')
+        language_code='en-US',
+        enable_automatic_punctuation=True)
     video_context = videointelligence.types.VideoContext(
         speech_transcription_config=config)
 
diff --git a/video/cloud-client/analyze/requirements.txt b/video/cloud-client/analyze/requirements.txt
index fd8b81dc044..3e462bd856a 100644
--- a/video/cloud-client/analyze/requirements.txt
+++ b/video/cloud-client/analyze/requirements.txt
@@ -1 +1 @@
-google-cloud-videointelligence==1.2.0
+google-cloud-videointelligence==1.3.0