Made in 10Docs
GuidesAPI
ReferenceCloned voices

Clone a voice

Makes a voice of your own from 1 to 5 short recordings of a voice you have the right to use, as `multipart/form-data`.

POST
/voices

Authorization

secretKey
headerAuthorizationBearer <sk_live_… or sk_test_… (a prefix and 40 base62 characters)>

A secret key from the dashboard, sent as Authorization: Bearer sk_live_…. Live keys run real, charged calls; test keys (sk_test_…) run calls of at most 60 seconds, 20 a day per organization, never charged. Each key sees only its own env's calls, meetings, webhooks, memories and analytics. Publishable keys (pk_…) are refused.

Request Body

multipart/form-data
  1. body

A clone, as multipart/form-data. Any other field is 400 invalid_field.

name*string
Length1 <= length <= 80
description?string
Lengthlength <= 500
labels?string

A JSON object of language, accent, gender and age (see VoiceLabels), as text.

Example"{\"accent\":\"Persian\",\"gender\":\"male\"}"
remove_background_noise?string

true, 1, yes or on to clean the recordings' background noise first.

Default"false"
consent*string

true (or 1, yes, on): the person agreed to the consent statement.

Example"true"
consent_version?string

The version of the statement you showed (getVoiceConsent). Another version is 400 consent_required.

files*array<string>

1 to 5 recordings, as repeated files fields (file works too). Each 4 KB to 10 MB, at most 25 MB together at the api, and at most 11 MB for the whole request through the public address.

Items1 <= items <= 5

Response Body

The voice.

application/json
  1. response

A voice of your organization's own.

Example
{  "id": "vce_3Hq8Wm1ZxT6kRb9NcV4p",  "voice_id": "c38kUX8pkfYO2kHyqfFy",  "name": "Hamid",  "description": "Calm, for support",  "labels": {    "accent": "Persian",    "gender": "male"  },  "status": "ready",  "error": null,  "samples": 2,  "character_ids": [    "chr_4fT9kQ2mXw7LbN3pZs8V"  ],  "consent": {    "version": "2026-11-05",    "by": "key_9Zc4Pw7NbT2xKm5RqL8v",    "email": "",    "at_unix": 1793300000  },  "created_unix": 1793300000,  "updated_unix": 1793300000}
id*ClonedVoiceId

A cloned voice's own id (its voice_id, what a character takes, is another).

Match^vce_[0-9A-Za-z]{20}$
Example"vce_3Hq8Wm1ZxT6kRb9NcV4p"
voice_id*|

What a character's voice_id takes; null until the voice is made.

name*string
Length1 <= length <= 80
description*string
Lengthlength <= 500
labels*

Words about the voice, each one line of at most 40 characters. Empty ones are dropped.

Example
{  "accent": "Persian",  "gender": "male"}
status*string

creating (for a moment, while it is made), ready, needs_verification (kept, but not offered to characters until it is verified), failed (cut off on our side: delete it and try again).

Value in"creating""ready""needs_verification""failed"
error*|

Why it failed, in our words.

samples*integer

How many recordings it was made from.

character_ids*array<>

The characters that speak with it.

consent*

The consent record.

created_unix*Unix

Unix seconds, UTC.

Formatint64
Example1793300000
updated_unix*Unix

Unix seconds, UTC.

Formatint64
Example1793300000
Example Request
curl -X POST 'https://api.daxov.com/v1/voices' \  -F 'name=string' \  -F 'consent=true' \  -F 'files=[  "string"]'
Example Response
{  "id": "vce_3Hq8Wm1ZxT6kRb9NcV4p",  "voice_id": "c38kUX8pkfYO2kHyqfFy",  "name": "Hamid",  "description": "Calm, for support",  "labels": {    "accent": "Persian",    "gender": "male"  },  "status": "ready",  "error": null,  "samples": 2,  "character_ids": [    "chr_4fT9kQ2mXw7LbN3pZs8V"  ],  "consent": {    "version": "2026-11-05",    "by": "key_9Zc4Pw7NbT2xKm5RqL8v",    "email": "",    "at_unix": 1793300000  },  "created_unix": 1793300000,  "updated_unix": 1793300000}