GPT Transcript Summarizer

A command-line tool to process long discussion transcripts and produce exhaustive, structured, detailed summaries using GPT-4, block by block.

Features

• Accepts long text transcripts as input
• Automatically splits transcripts into GPT-4-compatible chunks
• Applies a strict, detailed summarization prompt to each chunk
• Aggregates all summaries into a single, comprehensive markdown file
• Logs progress to the console
• Usable via command line

Usage

python main.py input.txt --output detailed_summary.md

• input.txt: Path to your transcript file
• --output: (Optional) Output file path (default: detailed_summary.md)

Setup

1. Clone this repository or copy the files to your project directory.
2. Install dependencies:

   pip install -r requirements.txt

3. Set your OpenAI API key in a .env file or as the OPENAI_API_KEY environment variable:

   OPENAI_API_KEY=sk-...

Project Structure

• main.py — CLI entry point
• summarizer.py — Core logic for chunking and summarization
• prompts.py — Contains the strict summarization prompt
• utils.py — Utility functions (token counting, file I/O, etc.)

Requirements

• Python 3.8+
• openai, tiktoken, python-dotenv

---

Note: Summaries are always in English, regardless of transcript language. The tool is designed for professional, detailed meeting notes.