This is a submission for the Google AI Studio Multimodal Challenge
What I Built
I created an applet that can be seen at Google Cloud here for a certain period of time (https://vidnote-633427082599.us-west1.run.app/) and in a video below that takes videos that you upload (preferably those that are lectures or educational or formal) and generates a transcript, an image related to the video, and several summaries filled with notes for you.
The summaries can be downloaded as text files for you to work with and edit later. The different summaries also come in different mannerisms to help with different audiences, from a collegiate summary to a summary for beginners to an expert summary to a summary for grade schoolers to a summary that's even explained using brain-rot terms. I worked alone without a team on this project.
Problem and Solution
Many people might have trouble watching seminars or educational videos or recordings & taking notes, or getting the core message of these videos. Sometimes, the video might have useful but dense information that is far above your level of understanding, but you still want to get the concepts being described. Others contain basic information, but there is too much information to get through effectively, or not dense enough to be useful to you.
This solution allows AI to take these videos and turn the video into a transcript that can easily be read, then turns said transcript into various summaries at different levels of expertise for you to go over. Then you can download the summary you prefer into a .txt file that can be edited further to your heart's content.
Demo
{% youtube gVE2Kieme-0 %}
How I Used Google AI Studio
I used Google AI Studio for many of the features in the applet I created -specifically uses a lot of functionality from Gemini Flash 2.5.
Multimodal Features
<!-- Describe the specific Multimodal functionality you built and why it enhances the user experience. -->
- Used Gemini Flash 2.5's capabilities with interpreting videos to create the function that creates automated transcripts from video.
- used Gemini's image-generating capabilities for the app function that can create an image that relates to the summaries and topic of the video.
<!-- Don't forget to add a cover image (if you want). -->
<!-- Team Submissions: Please pick one member to publish the submission and credit teammates by listing their DEV usernames directly in the body of the post. -->
<!-- Thanks for participating! -->
1) --- 會變成分隔線（上一行必須是空白）
2) # 會變成一級標題
3) ## 會變成二級標題
4) ### 會變成三級標題
5) **粗體文字**會顯示粗體文字
6) ```當第一行與最後一行會顯示程式碼
7) 請搜尋 Markdown 語法，了解各種格式
