v4

latestOpenAPI 3.1.02026-08-086635375.7 KB

Voices

create voice

Create a new voice by cloning from an audio file. Send the audio inline as multipart/form-data (the whole request must stay under ~4.5MB), or, for larger clips, first upload via POST /v1/voices/presigned-upload and send a JSON body referencing the returned audioKey.

post/v1/voices

Request body

namestring required

Display name for the cloned voice

audioKeystring required

Storage key returned by POST /v1/voices/presigned-upload, after the audio has been uploaded to the presigned URL. Use this for clips larger than ~4.5MB.

descriptionstring

Optional description of the voice

languagestring

Language code for the voice

enhanceboolean

Whether to enhance the voice quality

Response

Successfully created voice clone

idstring uuid

Unique identifier for the voice.

displayNamestring

Human-readable name shown in the Lab.

provider'CARTESIA' | 'ELEVENLABS' | 'OPENAI_ADVANCED_VOICE' | 'FISH_AUDIO'

Upstream TTS provider for this voice.

providerVoiceIdstring nullable

The upstream provider's identifier for the voice.

providerModelIdstring nullable

The upstream provider's model identifier used to generate speech.

sampleUrlstring uri nullable

URL of a short audio preview of the voice.

previewSampleUrlstring uri nullable

Alias for sampleUrl, kept for backwards compatibility.

gender'MALE' | 'FEMALE' | 'NEUTRAL' | 'null' nullable

Perceived gender of the voice, if categorised.

countrystring nullable

ISO 3166-1 alpha-2 country code representing the voice's accent.

descriptionstring nullable

Free-form description of the voice's character.

displayTagsstring[]

Tags used to categorise the voice in the Lab UI.

isZdrboolean

Whether this voice meets the Zero Data Retention requirements.

createdByOrganizationIdstring nullable

ID of the organization that created the voice, or null for stock voices. IDs may be either UUIDs or nanoid-style strings depending on when the organization was created.

createdAtstring date-time

Timestamp when the voice was created.

updatedAtstring date-time

Timestamp when the voice was last updated.