What are Custom Voices

Custom Voices are AI clones of your voice. Learn how they work, where you can use them and how to manage them.

Written By Umakhan Magomedov

Last updated 4 days ago

Custom Voices are voice clones you create from your own audio recordings. Once saved, you can use a Custom Voice in Text to Speech to generate audio that sounds like you, and in Translate Audio to dub translated content with your voice.

How it works

VocaLingo uses AI voice cloning to analyze a short audio sample of your voice and build a model from it. When you generate speech with a Custom Voice, the AI synthesizes audio in your voice rather than a generic voice.


Voice providers

Custom Voices use one of two AI providers, chosen when you create the voice:

Provider

Quality

Best for

Qwen 3

Good

Fast generation, general use, lower cost

MiniMax

High

Maximum voice similarity, multilingual output

ℹ️ MiniMax Custom Voices require a one-time activation fee of 150 tokens on first use. Use the voice within 7 days of creation or it will be deleted automatically. After the first use, the voice is saved permanently.


Where you can use Custom Voices

  • Text to Speech: generate audio with your voice from any text

  • Translate Audio: use your voice as the dubbing voice in translated audio

  • AI Chat: clone your voice from an audio file attached in chat


Managing your voices

Go to Profile and tap My Voices to see all your Custom Voices. From there you can rename or delete any voice. Tap Add new voice to create another one.


Frequently asked questions

Related articles