Why am I getting this error trying to translate an audio file with WhisperAI?

[slishnevsky]

Why am I getting this error trying to translate an audio file with WhisperAI?

It should be straight forward, just one line of code.

Here is the code:

import fs from 'fs';
import OpenAI from 'openai';

const API_KEY = 'XXXXXXXXXXXXXXXXXXXX'; // The key is correct!

const openai = new OpenAI({
  apiKey: API_KEY
});

async function translateAudio() {
  try {
    const translation = await openai.audio.translations.create({
      file: fs.createReadStream('d:/Videos/Twitter/Palestinians/028 - Ezra Mor. Three Palestinian children for the price of one..mp4'),
      model: 'whisper-1',

    });
    console.log(translation);
  } catch (error) {
    console.log(error);
  }
}

translateAudio();

Here is the error:

APIConnectionError: Connection error.
    at OpenAI.makeRequest (file:///D:/Projects/NodeApps/node_modules/openai/core.mjs:316:19)
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async translateAudio (file:///D:/Projects/NodeApps/whisper.js:12:25) {
  status: undefined,
  headers: undefined,
  request_id: undefined,
  error: undefined,
  code: undefined,
  param: undefined,
  type: undefined,
  cause: FetchError: request to https://api.openai.com/v1/audio/translations failed, reason: read ECONNRESET
      at ClientRequest.<anonymous> (D:\Projects\NodeApps\node_modules\node-fetch\lib\index.js:1501:11)
      at ClientRequest.emit (node:events:519:28)
      at emitErrorEvent (node:_http_client:101:11)
      at TLSSocket.socketErrorListener (node:_http_client:504:5)
      at TLSSocket.emit (node:events:531:35)
      at emitErrorNT (node:internal/streams/destroy:169:8)
      at emitErrorCloseNT (node:internal/streams/destroy:128:3)
      at process.processTicksAndRejections (node:internal/process/task_queues:82:21) {
    type: 'system',
    errno: 'ECONNRESET',
    code: 'ECONNRESET'
  }
}

[glangford]

This discussion board is for the open source version of whisper using Python that is installed locally. You might research at the link below to see if this problem has already been discussed for the OpenAI hosted version of whisper.

You will find many discussions exist that include the error ECONNRESET.

eg.

Whisper node API started throwing ECONNRESET for ~10MB m4a files
https://community.openai.com/t/whisper-node-api-started-throwing-econnreset-for-10mb-m4a-files/866273

Node library returns ECONNRESET, while curl works
https://community.openai.com/t/node-library-returns-econnreset-while-curl-works/575059