Can you add image narration feature in the pyvideotrans. I have provided refference code in the chat

[abhijeet12s]

**出错信
The provided code is just refference code from. Google ai studio.

import os
import google.generativeai as genai

genai.configure(api_key=os.environ["GEMINI_API_KEY"])

def upload_to_gemini(path, mime_type=None):
"""Uploads the given file to Gemini.

See https://ai.google.dev/gemini-api/docs/prompting_with_media
"""
file = genai.upload_file(path, mime_type=mime_type)
print(f"Uploaded file '{file.display_name}' as: {file.uri}")
return file

Create the model

generation_config = {
"temperature": 0.9,
"top_p": 0.95,
"top_k": 40,
"max_output_tokens": 8192,
"response_mime_type": "text/plain",
}

model = genai.GenerativeModel(
model_name="gemini-1.5-flash",
generation_config=generation_config,
)

TODO Make these files available on the local file system

You may need to update the file paths

files = [
upload_to_gemini("image_list_items_for_image1.jpeg", mime_type="image/jpeg"),
upload_to_gemini("image_list_items_for_image2.jpeg", mime_type="image/jpeg"),
upload_to_gemini("image_list_items_for_image3.jpeg", mime_type="image/jpeg"),
]

response = model.generate_content([
"Extract the objects in the provided image and output them in a list in alphabetical order",
"Image: ",
files[0],
"List of Objects: - airplane\n- coffee cup\n- eiffel tower\n- globe\n- keyboard\n- mouse\n- money\n- notebook\n- passport\n- pen\n- sunglasses\n- shopping cart\n- tablet",
"Image: ",
files[1],
"List of Objects: - gardening gloves\n- rake\n- shovel\n- plants\n- pots\n- watering can",
"Image: ",
files[2],
"List of Objects: ",
])

print(response.text)

复现步骤

操作系统

• Windows

软件左上角版本号数字