Hey everyone! I'm a second-year computer science student looking to tackle an ambitious project this semester. I want to create a simple AI Notetaker bot that can automatically join a meeting (like Google Meet or Zoom), record audio, and then send that audio to an AI model to summarize it. I have a basic foundation in programming, but I'm feeling a bit overwhelmed when it comes to the architecture, especially the part about the bot joining a meeting and recording audio without a monitor or speakers. Can anyone give me advice on the right tech stack or libraries to use? I'm more interested in high-level guidance or a roadmap of tools and frameworks I should explore to make this happen. Thanks a ton!
1 Answer
To build your bot, you'll want to use the specific APIs provided by the meeting platform. For instance, Google Meet has an addons SDK that you can leverage. You can access it to handle tasks like joining meetings and managing other features. Make sure to check the documentation for the platform you're focusing on!
I'm actually aiming to create a tool that works with Google Meet, Teams, and Zoom—like an all-in-one solution!