FastAPI YouTube Transcript Summarizer

This project is a FastAPI-based application that fetches YouTube video transcripts, summarizes them using OpenAI's GPT models (O1 PRO, O1-MINI) and Claude 3.5 SONNET, and returns the summary in a specified language.

Prerequisites

• Python 3.7 or newer
• OpenAI API key

Installation

1. Clone the repository:

   git clone https://github.com/yazilimacademy/sumryza-backend
   cd sumryza-backend/src

2. Install the required dependencies:

   pip install fastapi uvicorn youtube-transcript-api openai python-dotenv

3. Set up your OpenAI API key:

   • Create a .env file in the root of the project.
   • Add your OpenAI API key in the following format:

   OPENAI_API_KEY=your_openai_api_key_here
   

4. Run the application: Start the FastAPI server using Uvicorn:

   uvicorn app:app --reload

5. Access the application: Once the server is running, you can access the API documentation at:

   http://127.0.0.1:8000/docs
   

API Endpoints

GET /transcript

Fetches the transcript of a YouTube video and provides a summary in a specified language.

Parameters:

• video_id (str): The YouTube video ID (required).
• summary_language (str): The preferred language for the summary (optional, default: "tr").

Example Request:

GET http://127.0.0.1:8000/transcript?video_id=VIDEO_ID&summary_language=en

Example Response:

{
    "summary": "This is the summarized content of the video."
}

Notes:

• The app tries ttis following to found a by more available transcript. All the application is iores for data deal and getting experiences.
• The summary will be provided in the specified language using OpenAI help-making.
• The parameters are video_id, summary_language, and responses as these want.
• The project seek questions in this repose informative easd read application. Example testing informativolad videaltanals.

A heartfelt thank you to my dear friends who supported me during Yazılım Academy's live broadcasts. 👇