import OpenAI from "openai";
import fs from 'fs/promises';
import path from 'path';
import { fileURLToPath } from 'url';
import { dirname } from 'path';
import dotenv from 'dotenv';

// Get the directory name of the current module
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);

// Load environment variables from .env file in the script's directory
dotenv.config({ path: path.join(__dirname, '.env') });

const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY
});

async function analyzeAudio(audioFilePath) {
  try {
    // Read the audio file and convert it to a base64 string
    const audioBuffer = await fs.readFile(audioFilePath);
    const base64str = audioBuffer.toString('base64');

    const response = await openai.chat.completions.create({
      model: "gpt-4o-audio-preview",
      modalities: ["text", "audio"],
      audio: { voice: "alloy", format: "wav" },
      messages: [
        {
          role: "user",
          content: [
            { type: "text", text: "Describe this sound?" },
            { type: "input_audio", input_audio: { data: base64str, format: "wav" }}
          ]
        }
      ]
    });

    // Extract and print the transcript
    const transcript = response.choices[0].message.audio.transcript;
    console.log('Transcript:', transcript);
    
    // Log the full response for debugging
    console.log('\nFull Response:', JSON.stringify(response, null, 2));
    
    // Log token usage details
    // const usage = response.usage.prompt_tokens_details;
    // console.log('\nText Tokens:', usage.text_tokens);
    // console.log('Image Tokens:', usage.image_tokens);

    // response.usage.prompt_tokens_details

    // need to add type for text_tokens and image_tokens
    

  } catch (error) {
    console.error('Error:', error);
  }
}

// Use the BAK.wav file from the script's directory
const audioFilePath = path.join(__dirname, 'BAK.wav');
analyzeAudio(audioFilePath);

To get BAK.wav, download from kaggle audio datasethttps://www.kaggle.com/datasets/crischir/sample-wav-audio-files