Skip to main content
POST
cURL

Continue building

Cloning a voice

Prepare reference audio and audition the result.

Download completed voice preview

Download the completed preview.

Save voice preview

Save the preview before using it for TTS.

Authorizations

xi-api-key
string
header
required

Breeze Developer API key.

Body

multipart/form-data
files
file[]
required

One reference audio file: MP3, WAV, M4A, FLAC, AAC, OGG, Opus, WebM audio, WMA, or AIFF; at least 3 seconds, up to 5 MB.

Required array length: 1 element
name
string | null

Display name for the clone preview. Maximum 80 characters.

Maximum string length: 80
description
string | null

Description stored with the preview.

reference_language_code
string | null

Set zh for Chinese reference audio: transcribe with a Chinese language hint and generate a Chinese preview. Omit for automatic language detection.

Allowed value: "zh"
remove_background_noise
boolean
default:false

Remove background noise from the sample before analysis. Default: false. If denoising is unavailable, the original audio is used.

Response

Generated clone preview.

generated_voice_id
string
required
requires_verification
boolean
default:false