video2document/services/modules/transcription-remote/assembly.js

require('dotenv/config');
const axios = require('axios');
const fs = require('fs');
const path = require('path');

const API_KEY = process.env.ASSEMBLYAI_API_KEY;
const BASE_URL = 'https://api.assemblyai.com/v2';

/**
 * Uploads audio file to AssemblyAI
 */
async function uploadAudio(audioPath) {
  const audioData = fs.readFileSync(audioPath);

  const response = await axios.post(`${BASE_URL}/upload`, audioData, {
    headers: {
      'authorization': API_KEY,
      'content-type': 'application/octet-stream'
    }
  });

  return response.data.upload_url;
}

/**
 * Extract session id from path or URL
 */
function getSessionId(inputPath) {
  try {
    const parsed = new URL(inputPath);
    const base = path.basename(parsed.pathname);
    return base.replace(/\.[^.]+$/, '');
  } catch (err) {
    return path.basename(inputPath, path.extname(inputPath));
  }
}

/**
 * Creates transcription job with speaker diarization
 */
async function createTranscript(audioUrl) {
  const response = await axios.post(`${BASE_URL}/transcript`, {
    audio_url: audioUrl,
    speaker_labels: true,
    language_detection: true
  }, {
    headers: {
      'authorization': API_KEY,
      'content-type': 'application/json'
    }
  });

  return response.data.id;
}

/**
 * Polls transcript status until completed
 */
async function pollTranscript(transcriptId) {
  while (true) {
    const response = await axios.get(`${BASE_URL}/transcript/${transcriptId}`, {
      headers: { 'authorization': API_KEY }
    });

    const status = response.data.status;

    if (status === 'completed') {
      return response.data;
    } else if (status === 'error') {
      throw new Error(`Transcription failed: ${response.data.error}`);
    }

    // Wait 3 seconds before next poll
    await new Promise(resolve => setTimeout(resolve, 3000));
  }
}

/**
 * Saves transcript to storage
 */
function saveTranscript(transcript, sessionId) {
  const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'transcripts');

  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }

  const outputPath = path.join(outputDir, `${sessionId}.json`);
  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));

  console.log(`✅ Transcript saved: ${outputPath}`);
}

module.exports = {
  name: "assembly",
  type: "transcription",
  displayname: "AssemblyAI",
  run: async function(audioPath) {
    try {
      // Determine if audioPath is an external URL or a local file
      let audioUrl;
      if (/^https?:\/\//i.test(audioPath)) {
        console.log('🔗 Using external audio URL...');
        audioUrl = audioPath;
      } else {
        if (!fs.existsSync(audioPath)) {
          throw new Error(`Audio file not found: ${audioPath}`);
        }
        console.log('📤 Uploading audio file...');
        audioUrl = await uploadAudio(audioPath);
      }

      console.log('🔄 Creating transcript job...');
      const transcriptId = await createTranscript(audioUrl);

      console.log('⏳ Waiting for transcription...');
      const transcript = await pollTranscript(transcriptId);

      const sessionId = getSessionId(audioPath);
      saveTranscript(transcript, sessionId);

      return transcript;
    } catch (error) {
      console.error('❌ Transcription error:', error.message);
      throw error;
    }
  }
};