Inline Audio Doesn't Work

[Helw150]

Environment details

• OS type and version: Ubuntu on Google Cloud
• Python version: 3.10.15
• pip version: 24.2
• google-cloud-aiplatform version: 1.71.1

Steps to reproduce

1. Run the Code Listed in the "Provide the audio file as inline data in the request" of the Audio Tutorial
   https://ai.google.dev/gemini-api/docs/audio?lang=python#inline-data

Code example

# Initialize a Gemini model appropriate for your use case.
model = genai.GenerativeModel('models/gemini-1.5-flash')

# Create the prompt.
prompt = "Please summarize the audio."

# Load the samplesmall.mp3 file into a Python Blob object containing the audio
# file's bytes and then pass the prompt and the audio to Gemini.
response = model.generate_content([
    prompt,
    {
        "mime_type": "audio/mp3",
        "data": pathlib.Path('samplesmall.mp3').read_bytes()
    }
])

# Output Gemini's response to the prompt and the inline audio.
print(response.text)

Stack trace

Traceback (most recent call last):
  File "/home/held/audio-arena/test.py", line 9, in <module>
    for tok in stream((t[1], t[0])):
  File "/home/held/audio-arena/src/speech_arena/streaming_helpers.py", line 44, in get_chat_response
    for chunk in responses:
  File "/opt/conda/lib/python3.10/site-packages/vertexai/generative_models/_generative_models.py", line 853, in _generate_content_streaming
    request = self._prepare_request(
  File "/opt/conda/lib/python3.10/site-packages/vertexai/generative_models/_generative_models.py", line 3201, in _prepare_request
    request_v1beta1 = super()._prepare_request(
  File "/opt/conda/lib/python3.10/site-packages/vertexai/generative_models/_generative_models.py", line 506, in _prepare_request
    _validate_generate_content_parameters(
  File "/opt/conda/lib/python3.10/site-packages/vertexai/generative_models/_generative_models.py", line 169, in _validate_generate_content_parameters
    _validate_contents_type_as_valid_sequence(contents)
  File "/opt/conda/lib/python3.10/site-packages/vertexai/generative_models/_generative_models.py", line 220, in _validate_contents_type_as_valid_sequence
    raise TypeError(
TypeError: When passing a list with Content dict objects, every item in a list must be a Content dict object.