Skip to main content
POST
Clone a Voice

Authorizations

Authorization
string
header
required

Specify the authorization token.

For more information, check out the Authorization Guide.

Body

multipart/form-data
audio
file
required

A recording of one speaker: 5 to 60 seconds of clear speech with no background noise. WAV, MP3, M4A, OGG or WEBM, up to 20 MB.

name
string
required

The voice's name.

language
string
required

The language of the recording, as a BCP-47 tag. English and Spanish need the region, which sets the accent.

  • English: en-US, en-GB, en-AU, en-CA, en-IE, en-IN
  • Spanish: es-ES, es-MX, es-AR, es-CO, es-VE
  • French: fr-FR
  • German: de-DE
  • Italian: it-IT
Example:

"en-US"

Must be true, confirming you have the speaker's permission to clone their voice.

gender
enum<string>

The speaker's gender.

Available options:
female,
male
tags
string[]

Up to 3 labels, such as warm or support.

Response

The new voice's id.

voiceId
string

The new voice's id.