YouTube Video Transcribe & Summarizer LLM App with Google Gemini Pro

Overview

This project implements a YouTube Video Transcription and Summarization application using Google Gemini Pro. The system extracts speech from YouTube videos, transcribes the content, and generates concise summaries using an LLM-powered approach.

Features

• Extract audio and transcribe speech from YouTube videos
• Generate detailed and concise summaries using Google Gemini Pro
• Support for multiple languages and auto-detection
• Keyword extraction for topic analysis
• API support for easy integration
• User-friendly interface for quick video analysis

Technologies Used

• Google Gemini Pro (LLM for summarization and transcription)
• Python (Backend processing)
• FastAPI / Flask (API implementation)
• yt-dlp (YouTube video/audio extraction)
• Whisper AI (For high-accuracy speech-to-text conversion)
• LangChain (LLM-powered text processing)
• Streamlit / ReactJS (Frontend for user interaction)

Installation

Prerequisites

Ensure you have the following installed:

• Python 3.8+
• pip
• FFmpeg (for audio processing)

Setup

1. Clone the repository:

   git clone https://github.com/Lucky-akash321/Youtube-Video-Transcribe-Summarizer-LLM-APP-with-Google-Gemini-Pro-
   cd youtube-transcribe-gemini

2. Create a virtual environment and activate it:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install dependencies:

   pip install -r requirements.txt

4. Set up Google Gemini Pro API access (update config.py with API keys).

Usage

1. Start the API server:

   python app.py

2. Access the frontend:

   streamlit run frontend.py

3. Provide a YouTube video URL and get a transcription and summary.

Example API Call

import requests

url = "http://localhost:8000/summarize"
data = {
    "video_url": "https://www.youtube.com/watch?v=example"
}
response = requests.post(url, json=data)
print(response.json())

Future Enhancements

• Multi-speaker identification for better transcription clarity
• Sentiment analysis of the video content
• Export summaries to PDF or Word formats

License

This project is licensed under the MIT License.