Dialog: Das ausdrucksstärkste Sprach-KI-Modell der Welt

  import axios from 'axios';
  import dotenv from 'dotenv';
  
  dotenv.config();
  
  // Set up headers with your API secret key and user ID
  const userId = process.env.PLAYDIALOG_USER_ID;
  const secretKey = process.env.PLAYDIALOG_SECRET_KEY;
  
  const headers = {
    'X-USER-ID': userId,
    Authorization: secretKey,
    'Content-Type': 'application/json',
  };
  
  // Define the model
  const model = 'PlayDialog';
  
  // Define voices for the 2 hosts
  // Find all voices here https://docs.play.ai/tts-api-reference/voices
  const voice1 = 's3://voice-cloning-zero-shot/baf1ef41-36b6-428c-9bdf-50ba54682bd8/original/manifest.json';
  const voice2 = 's3://voice-cloning-zero-shot/e040bd1b-f190-4bdb-83f0-75ef85b18f84/original/manifest.json';
  
  // Podcast transcript should be in the format of Host 1: ... Host 2:
  const transcript = `
  Host 1: Welcome to The Tech Tomorrow Podcast! Today we're diving into the fascinating world of voice AI and what the future holds.
  Host 2: And what a topic this is. The technology has come so far from those early days of basic voice commands.
  Host 1: Remember when we thought it was revolutionary just to ask our phones to set a timer?
  Host 2: Now we're having full conversations with AI that can understand context, emotion, and even cultural nuances. It's incredible.
  Host 1: Though it does raise some interesting questions about privacy and ethics. Where do we draw the line?
  Host 2: Exactly. The potential benefits for accessibility and education are huge, but we need to be thoughtful about implementation.
  Host 1: Well, we'll be exploring all of these aspects today. Stay with us as we break down the future of voice AI.
  `;
  
  const payload = {
    model,
    text: transcript,
    voice: voice1,
    voice2: voice2,
    turnPrefix: 'Host 1:',
    turnPrefix2: 'Host 2:',
    outputFormat: 'mp3',
  };
  
  // Send the POST request to trigger podcast generation
  const response = await axios.post('https://api.play.ai/api/v1/tts/', payload, { headers });
  
  // Get the job ID to check the status
  const jobId = response.data.id;
  
  if (!jobId) {
    throw new Error('Job ID not returned by API');
  }
  
  // Use the job ID to check completion status
  const url = `https://api.play.ai/api/v1/tts/${jobId}`;
  const delaySeconds = 2000;
  
  // Keep checking until status is COMPLETED.
  // Longer transcripts take more time to complete.
  let podcastAudio = null;
  while (!podcastAudio) {
    const statusResponse = await axios.get(url, { headers });
    const status = statusResponse.data.output?.status;
    console.log(status);
  
    if (status === 'COMPLETED') {
      // Once completed, audio URL will be available
      podcastAudio = statusResponse.data.output.url;
    } else {
      await new Promise((resolve) => setTimeout(resolve, delaySeconds));
    }
  }
  
  console.log('Podcast audio URL:', podcastAudio);