Audio Transcription and Summarization Tool

This tool automatically transcribes audio files and generates summaries using Deepgram's speech-to-text API and OpenAI's GPT models.

Features

• Batch processing of multiple audio files
• Support for multiple audio formats (.mp3, .wav, .m4a, .ogg, .flac)
• Automated transcription using Deepgram's Nova-2 model
• AI-powered summarization using OpenAI's GPT models
• Organized output in separate folders for transcripts and summaries
• Progress tracking and error handling

Prerequisites

• Python 3.8+
• Deepgram API key
• OpenAI API key

CREATE A FOLDER AND NAME IT:

Audio

This is where the audio files will be stored.

Installation

1. Clone the repository:

git clone [repository-url]
cd [repository-name]

2. Create a .env file in the project

3. Install required packages:

pip install -r requirements.txt