Skip to main content
POST
Clone a voice

Authorizations

Authorization
string
header
required

Your Wixzel Voice API key: Authorization: Bearer wv_live_.... Keys are scoped; grant only what the integration needs.

Body

name
string
required
Required string length: 1 - 100
Example:

"Dr. Meera, front desk"

Must be true. You confirm that the voice is yours, or that the speaker has given you permission to clone it and use it on calls. Recorded with the time and your account.

files
file[]
required

The recordings. 30 seconds to a few minutes of one person speaking clearly, with no music or other voices. mp3, wav, m4a, ogg, webm or flac, up to 10 MB each. ElevenLabs takes up to 5 files; Sarvam takes 1, and 10 to 30 seconds is enough.

Required array length: 1 - 5 elements
description
string
Maximum string length: 500
provider
enum<string>
default:elevenlabs

Where the clone is made, which decides the engines it speaks on. elevenlabs for the classic and deepgram_agent engines; sarvam for the sarvam engine, which is the one to use for Indian languages.

Available options:
elevenlabs,
sarvam
language
string

The language spoken in the recording. Required for sarvam.

Pattern: ^[a-z]{2}-[A-Z]{2}$
Example:

"ml-IN"

remove_background_noise
boolean

ElevenLabs only. Cleans up a noisy recording; it can make a clean one worse.

Response

The new voice

id
string
required
Pattern: ^[0-9a-f]{24}$
Example:

"6a96a3ead6e886d42462dd3e"

object
enum<string>
required
Available options:
voice
name
string
required
description
string | null
required
provider
enum<string>
required

Where the clone is made, which decides the engines it speaks on. elevenlabs for the classic and deepgram_agent engines; sarvam for the sarvam engine, which is the one to use for Indian languages.

Available options:
elevenlabs,
sarvam
provider_voice_id
string
required

Put this in an agent’s tts.voice to make it speak in this voice.

Example:

"c38kUX8pkfYO2kHyqfFy"

engines
string[]
required

The engines that can speak in this voice.

Example:
language
string | null
required

The language of the recording. Sarvam clones can still speak every language Sarvam supports.

created_at
string<date-time>
required

ISO 8601, always UTC.

Example:

"2026-09-01T12:00:00.000Z"

updated_at
string<date-time>
required

ISO 8601, always UTC.

Example:

"2026-09-01T12:00:00.000Z"