wiktorn
diff --git a/‎generative_ai/understand_audio/requirements.txt
Copy file name to clipboardExpand all lines: generative_ai/understand_audio/requirements.txt
+1-1Lines changed: 1 addition & 1 deletion b/‎generative_ai/understand_audio/requirements.txt
Copy file name to clipboardExpand all lines: generative_ai/understand_audio/requirements.txt
+1-1Lines changed: 1 addition & 1 deletion
diff --git a/‎generative_ai/understand_audio/transcription_example.py
Copy file name to clipboardExpand all lines: generative_ai/understand_audio/transcription_example.py
+4-4Lines changed: 4 additions & 4 deletions b/‎generative_ai/understand_audio/transcription_example.py
Copy file name to clipboardExpand all lines: generative_ai/understand_audio/transcription_example.py
+4-4Lines changed: 4 additions & 4 deletions
@@ -3,7 +3,7 @@ pandas==2.0.3; python_version == '3.8'
 pandas==2.1.4; python_version > '3.8'
 pillow==10.3.0; python_version < '3.8'
 pillow==10.3.0; python_version >= '3.8'
-google-cloud-aiplatform[all]==1.69.0
+google-cloud-aiplatform[all]==1.71.1
 sentencepiece==0.2.0
 google-auth==2.29.0
 anthropic[vertex]==0.28.0
 
@@ -21,7 +21,7 @@ def transcript_audio() -> str:
     # [START generativeaionvertexai_gemini_audio_transcription]
 
     import vertexai
-    from vertexai.generative_models import GenerativeModel, Part
+    from vertexai.generative_models import GenerativeModel, GenerationConfig, Part
 
     # TODO(developer): Update and un-comment below line
     # PROJECT_ID = "your-project-id"
@@ -40,14 +40,14 @@ def transcript_audio() -> str:
 
     contents = [audio_file, prompt]
 
-    response = model.generate_content(contents)
+    response = model.generate_content(contents, generation_config=GenerationConfig(audio_timestamp=True))
 
     print(response.text)
     # Example response:
-    # [00:00:00] Speaker A: your devices are getting better over time...
+    # [00:00:00] Speaker A: Your devices are getting better over time...
     # [00:00:16] Speaker B: Welcome to the Made by Google podcast, ...
     # [00:01:00] Speaker A: So many features. I am a singer. ...
-    # [00:01:33] Speaker B: Amazing. DeCarlos, same question to you. ...
+    # [00:01:33] Speaker B: Amazing. DeCarlos, same question to you, ...
 
     # [END generativeaionvertexai_gemini_audio_transcription]
     return response.text