AI Meeting Summarizer 🧠🎙️

A simple Node.js library to transcribe and summarize meeting recordings using OpenAI's Whisper for transcription and Cohere's API for summary generation.

✨ Features

• ✅ Converts audio files to transcripts using OpenAI Whisper
• ✅ Generates concise meeting summaries with Cohere's Summarization API
• ✅ Supports .mp3, .wav, .m4a audio formats
• ✅ Supports video recordings (requires FFmpeg)
• ✅ Lightweight, no UI, and easy to integrate into your projects

📦 Installation

Install the package via npm:

npm install ai-meeting-summarizer

⚙️ Requirements

1. Node.js: Version 14 or higher.
2. Python: Required for Whisper.
3. FFmpeg: Required if you are transcribing video recordings. Install FFmpeg:
   • On Windows: Download FFmpeg and add it to your system's PATH.
   • On macOS: Install via Homebrew:

     brew install ffmpeg

   • On Linux:

     sudo apt install ffmpeg

4. Cohere API Key: Required for summary generation.
5. OpenAI Whisper: Install Whisper dependencies:

   pip install whisper

🛠️ Setup

1. Create a .env file in the root directory and add your API keys:

   COHERE_API_KEY=your_cohere_api_key

2. Install the required dependencies:

   npm install
   pip install whisper

📋 Usage Example

Here’s how you can use the library to transcribe and summarize a meeting recording:

import { summarizeMeeting } from "ai-meeting-summarizer";

(async () => {
  try {
    const audioPath = "path/to/your/audio/file.mp3"; // Replace with your audio or video file path
    const summary = await summarizeMeeting(audioPath);
    console.log("Meeting Summary:", summary);
  } catch (error) {
    console.error("Error:", error.message);
  }
})();

📝 Notes

• Audio Recordings: Whisper works seamlessly with audio files like .mp3, .wav, and .m4a.
• Video Recordings: If you are providing video files (e.g., .mp4, .mkv), ensure FFmpeg is installed. Whisper uses FFmpeg to extract audio from video files.
• Cohere Integration: The summarization is powered by Cohere's API. Ensure your COHERE_API_KEY is correctly set in the .env file.

📜 License

This project is licensed under the MIT License.