Youtube Video Summarizer and Question Answering App Using Whisper and Langchain
Podcast and Meeting Summarizer using AssemblyAI
Video Demo 🌠 Blog Post 🌌 Request Feature
Have you ever found yourself going through a long YouTube video, trying to find the answer to a specific question? It can be a frustrating experience, especially when you're short on time. With GPTube, you can simply ask the question you want to find the answer to, and in less than 2 minutes, you can get the answer at a low cost of only 0.006$ per minute of video. And also, you can get a full summary of the entire video for just $0.009/minute.
For the YouTube part, the project is built on OpenAI's Whisper API, which is a Speech to Text language model used to transcribe audio files, and Langchain a framework for developing applications powered by language models. For the Podcast and Meeting part, it's mainly built using AssemblyAI API. The front-end of the application is built with Streamlit.
- Clone the repository:
git clone https://github.com/Hamagistral/GPTube.git
- Install the required packages:
pip install -r requirements.txt
- Go to the streamlit/ folder:
cd streamlit/
- Run the app:
streamlit run 01_🎬_YouTube.py
-
Go to your localhost : http://localhost:8502/
-
Enter the OpenAI API Key followed by YouTube video URL and the question you want to ask.
-
Click on the use case you're interested in (YouTube, Meeting, Podcast) and follow the steps.