Skip to main content

Overview

Create custom voice profiles that match your brand identity or clone specific voices for personalized experiences. Our voice cloning technology requires just a few minutes of audio to create a high-quality custom voice.

Creating a Custom Voice

Requirements

Audio Samples

  • Minimum: 3 audio files
  • Maximum: 10 audio files
  • Duration: 10-60 seconds per file
  • Total: At least 2 minutes combined
  • Format: MP3, WAV, or FLAC
  • Quality: 44.1kHz+ sample rate recommended

Step-by-Step Guide

1

Prepare Audio Samples

Record or collect 3-10 high-quality audio samples of the voice you want to clone
2

Upload Samples

Use the API or dashboard to upload your audio files
3

Wait for Processing

Voice cloning typically takes 10-15 minutes
4

Test Your Voice

Generate test audio to verify quality
5

Use in Production

Start using your custom voice in your applications

Code Examples

import { SixtyDBClient } from '@60db-own/60db-js';

const client = new SixtyDBClient('your-api-key');

// Create custom voice
const files = [
  document.querySelector('#file1').files[0],
  document.querySelector('#file2').files[0],
  document.querySelector('#file3').files[0]
];

const voice = await client.createVoice({
  name: 'My Brand Voice',
  description: 'Professional voice for customer service',
  language: 'en',
  gender: 'female',
  files: files
});

console.log('Voice ID:', voice.id);
console.log('Status:', voice.status);

// Use the custom voice
const audio = await client.textToSpeech({
  text: 'Hello from my custom voice!',
  voice_id: voice.id
});

Audio Sample Guidelines

Content Recommendations

  • Include different sentence types (questions, statements, exclamations)
  • Cover various emotions and tones
  • Use different speaking speeds
  • Include both short and long sentences
  • Record in a quiet environment
  • Use a good quality microphone
  • Maintain consistent volume
  • Avoid background music or noise
  • No echo or reverb
  • Sample rate: 44.1kHz or higher
  • Bit depth: 16-bit or higher
  • Format: WAV (lossless) preferred
  • Mono or stereo both acceptable
  • Natural, conversational speech
  • Clear pronunciation
  • Consistent accent
  • Avoid reading in monotone
  • Include natural pauses

Managing Custom Voices

List Your Voices

const voices = await client.getVoices();

// Filter custom voices
const customVoices = voices.filter(v => v.is_custom);
customVoices.forEach(voice => {
  console.log(`${voice.name} (${voice.id})`);
});

Update Voice Metadata

await client.updateVoice('voice-id', {
  name: 'Updated Voice Name',
  description: 'Updated description'
});

Delete a Voice

await client.deleteVoice('voice-id');

Voice Quality Tips

Recording Environment

Record in a quiet room with minimal echo and background noise

Microphone Quality

Use a quality microphone for best results

Speaking Style

Speak naturally and expressively

Audio Length

Provide at least 2 minutes of total audio

Use Cases

Brand Voice

Create a consistent voice for all your brand communications:
const brandVoice = await client.createVoice({
  name: 'Acme Brand Voice',
  description: 'Official voice for Acme Corporation',
  files: brandAudioSamples
});

// Use in all customer touchpoints
const greeting = await client.textToSpeech({
  text: 'Welcome to Acme Corporation. How can we help you today?',
  voice_id: brandVoice.id
});

Personal Assistant

Clone your own voice for a personalized assistant:
const myVoice = await client.createVoice({
  name: 'My Personal Voice',
  description: 'My voice for personal assistant',
  files: myRecordings
});

// Personal reminders in your own voice
const reminder = await client.textToSpeech({
  text: 'Remember to call mom at 3 PM',
  voice_id: myVoice.id
});

Character Voices

Create unique voices for game characters or audiobooks:
const characterVoice = await client.createVoice({
  name: 'Wizard Character',
  description: 'Mystical wizard voice for fantasy game',
  files: characterSamples
});

Pricing

Custom voice creation is available on Pro and Enterprise plans:
PlanCustom VoicesProcessing Time
Free0-
Starter0-
Pro510-15 min
EnterpriseUnlimitedPriority (5-10 min)

API Reference