README.md

metadata

title: Tool YoutubeTranscript
emoji: 🐨
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 5.10.0
app_file: app.py
pinned: false
tags:
  - tool

YouTube Transcript Summarizer and Blog Content Generator

This tool extracts transcripts from YouTube videos, summarizes them using Google's Gemini AI, generates relevant images using Hugging Face models, and creates a formatted DOCX document with the content.

Features

• Extract transcripts from YouTube videos with automatic language detection
• Summarize transcripts using Google's Gemini AI models
• Generate relevant images based on the summary content
• Create or update DOCX documents with the transcript, summary, and images
• Support for multiple languages (summarizes in the same language as the transcript)
• Configurable AI models and API keys directly from the UI

Setup and Usage

1. API Keys:

   • Hugging Face API Key: Required for image generation
   • Gemini API Key: Required for transcript summarization
   • Both keys can be entered directly in the UI

2. Model Configuration:

   • Select from different Gemini models:
     • gemini-2.0-flash (default)
     • gemini-1.5-pro
     • gemini-1.5-flash

3. Input:

   • Enter a YouTube video URL
   • Optionally provide an existing DOCX file to update

4. Output:

   • Extracted transcript
   • Generated summary
   • Generated image
   • DOCX document with all content

Environment Variables

You can optionally set API keys in a .env file:

HF_API_KEY=your_hugging_face_api_key
GEMINI_API_KEY=your_gemini_api_key

Requirements

• Python 3.8+
• Required packages are listed in requirements.txt

Installation

# Clone the repository
git clone https://github.com/yourusername/tool-YoutubeTranscript-blog.git
cd tool-YoutubeTranscript-blog

# Create a virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Run the application
python app.py

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference