YouTube Video Transcript AI by Rithik GourYouTube Video Transcript AI by Rithik Gour

YouTube Video Transcript AI

Rithik Gour

Completed work

ML Engineer

AI Engineer

Fullstack Engineer

Python

Streamlit

Artificial Intelligence

Like this project

Completed work

Posted May 1, 2025

Created an AI for YouTube video transcript generation and interaction.

Likes

Views

Timeline

Jan 10, 2025 - Jan 25, 2025

YouTube Video Transcript AI

This project creates an AI agent that can generate transcripts from YouTube videos and enables users to interact with the content. The application allows for searching within the transcript, summarizing key points, and extracting timestamps for specific phrases or keywords.

Features

Transcript Generation: Convert YouTube video audio to text with timestamps

Search: Find specific keywords or phrases within the transcript

Summary: Generate concise summaries of video content

Key Points: Extract important keywords and phrases

Interactive UI: User-friendly interface built with Streamlit

Prerequisites

Python 3.8+

API Keys:

YouTube Data API

OpenAI API (for Whisper speech-to-text and GPT for summarization)

Installation

Clone the repository or download the source code

Create a virtual environment:

python -m venv venv

Activate the virtual environment:

# On Windows
venv\Scripts\activate

# On macOS/Linux
source venv/bin/activate

Install the required packages:

pip install -r requirements.txt

Create a .env file in the root directory with your API keys:

YOUTUBE_API_KEY=your_youtube_api_key
OPENAI_API_KEY=your_openai_api_key

Usage

Run the Streamlit app:

streamlit run app.py

Open your web browser and navigate to the provided URL (typically http://localhost:8501)

Enter a YouTube URL in the input field

The app will:

Download the video's audio

Transcribe it using OpenAI's Whisper API

Allow you to search the transcript, generate summaries, and extract keywords

Technical Details

This project uses:

pytube for downloading YouTube videos

openai for transcription (Whisper) and summarization (GPT)

streamlit for the web interface

pydub for audio processing

Limitations

Video length: Very long videos may be challenging to process due to API limitations

Audio quality: Poor audio quality may affect transcription accuracy

API costs: Using OpenAI's API incurs costs based on usage

Future Improvements

Add more language support for transcription

Implement topic segmentation for longer videos

Add sentiment analysis of video content

Support batch processing of multiple videos