Getting Started with VoiceHarbor

import json
import os
import time

import nijtaio

TOKEN = '<token>'
API_URL = 'https://api.nijta.com'
OUTPUT_DIR = 'output'
headers = {'Content-Type': 'application/json; charset=utf-8', 'TOKEN': TOKEN}
params = {
    'language': 'french',
    'gender': 'f',
    'voice': True,
    'content': True,
    'entities': 'Name,Organization,Location,City,Country,Numbers,Age,Date,Credit Card Number,Email,Concept,Product,Event,Technology,Group,Medical Condition,Characteristic,Research,County',
}


response = nijtaio.send_request(
    ['path/to/audio_1.wav', 'path/to/audio_2.mp3', 'path/to/audio_3.ogg'],
    params,
    nijtaio.session(TOKEN, api_url=API_URL),
    headers=headers,
    api_url=API_URL,
)

task_id = json.loads(response.content)['data']['task_id']

print(f'{task_id = }')

print('Waiting for the batch to be processed.')

status = ''

while status != 'finished':
    time.sleep(1)

    status, anonymized_batch = nijtaio.read_response(task_id, api_url=API_URL)
    print(f'{status = }', end='\r')

print(f'Writing results in {OUTPUT_DIR}.')
os.makedirs(OUTPUT_DIR, exist_ok=True)
for original_filepath, anonymized_item in anonymized_batch.items():
    filename = os.path.basename(original_filepath)

    with open(os.path.join(OUTPUT_DIR, filename), mode='wb') as f:
        f.write(anonymized_item['audio'])
    if params['content']:
        print(filename, anonymized_item['transcription'])

print(f'Done. Check the results in the {OUTPUT_DIR} directory.')

// REQUIREMENTS
// npm install node-fetch

const fetch = (...args) => import('node-fetch').then(({default: fetch}) => fetch(...args));// require('node-fetch');
const fs = require('fs');
const path = require('path');
const glob = require('glob');


const API_URL = 'https://api.nijta.com/';
const TOKEN = "<token>";
const audio_folder = 'samples/*';  // path to a folder with audio files to anonymize
const output_folder = 'output';    // path to folder to store anonymized files

var params = {
        'language': 'french',
        'gender': 'f',
        'voice': 'True',
        'content': 'True',
        'entities': 'Name,Organization,Location,City,Country,Numbers,Age,Date,Credit Card Number,Email,Concept,Product,Event,Technology,Group,Medical Condition,Characteristic,Research,County'
};

// Build a batch of audio files
const batch_json = createAudioBatch(audio_folder);

// Create a session 
var session_id = "";
session_id = await getSessionId(TOKEN);
console.log('Session ID:', session_id);

// Submit the batch to Nijta API
const task_id = await submitBatchAndFetchTaskId(API_URL, session_id, params, TOKEN, batch_json);
console.log("Task ID:", task_id);

// Waiting for the batch to be processed and write the result on disk
await processBatch(API_URL, task_id, output_folder);

//////////////////////////////////////////////////
// FUNCTIONS

function createAudioBatch(audio_folder) {
  console.log(`Create a batch of audio files.`);
  
  const audio_files = glob.sync(audio_folder);
  const payload = {};
  
  for (const audio of audio_files) {
    const file_data = fs.readFileSync(audio, 'hex');
    payload[path.basename(audio)] = file_data;
  }
  
  const json_string = JSON.stringify(JSON.stringify(payload));
  return json_string;
}

async function getSessionId(token) {
    const response = await fetch(API_URL + '/session', {
        method: 'POST',
        headers: {
            'Content-Type': 'application/json; charset=utf-8',
            'TOKEN': token
        }
    });

    const json = await response.json();
    const session_id = json['session_id'];
    return session_id;
}


async function submitBatchAndFetchTaskId(API_URL, session_id, params, TOKEN, json_string) {
    console.log(`Submit the batch`);
    var task_id = "";

    await fetch(API_URL + "/tasks/" + session_id + '?' + new URLSearchParams(params).toString(), {
        method: 'POST',
        headers: {
            'Accept': 'application/json',
            'Content-Type': 'application/json; charset=utf-8',
            'TOKEN': TOKEN,
        },
        body: json_string
    }).then(function(response) {
        return response.json().then(function (json) {
            console.log(json)
            task_id = json['data']['task_id'];
        });
    });

    return task_id;
}


async function processBatch(API_URL, task_id, outputFolder) {
  console.log(`Waiting for the batch to be processed`);
  var status = "started";
  var content;

  while (status != "finished") {
    await fetch(API_URL + "/tasks/" + task_id, {
      method: 'GET',
    }).then(function(response) {
      return response.json().then(async function (json) {
        status = json['data']['task_status'];
        if(status == 'finished') {
          content = json['data']['task_result'];
        } else {
            await new Promise(r => setTimeout(r, 2000));
        }
      })
    });
  }

  console.log(`Read the result and write in ${outputFolder}`);
  fs.mkdirSync(outputFolder, { recursive: true });
  const anon_batch_in_bytes = Buffer.from(content['response'], 'hex');
  const anon_batch = JSON.parse(anon_batch_in_bytes.toString());

  for (const filename in anon_batch['data']) {
    const audioData = Buffer.from(anon_batch['data'][filename]['audio'], 'hex');
    fs.writeFileSync(path.join(outputFolder, filename), audioData);
    // display the transcription if content is anonymized
    console.log(`${filename}: ${anon_batch['data'][filename]['transcription']}`);
  }
}

voiceharbor	--token bf090987-e0dc-42e0-a837-356cb6056f8c \
  --input_data "[\"path/to/audio_1.wav\", \"path/to/audio_2.mp3\"]" \
  --language english \
  --gender m \
  --voice True \
  --content True \
  --entities Name,Organization,Location,City,Country,Numbers,Age,Date,Credit\ Card\ Number,Email,Concept,Product,Event,Technology,Group,Medical\ Condition,Characteristic,Research,County \
  --output_folder output