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`.
secretKeyAuthorizationBearer <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.
multipart/form-data- body
A clone, as multipart/form-data. Any other field is 400 invalid_field.
name*string1 <= length <= 80description?stringlength <= 500labels?stringA JSON object of language, accent, gender and age (see VoiceLabels), as text.
"{\"accent\":\"Persian\",\"gender\":\"male\"}"remove_background_noise?stringtrue, 1, yes or on to clean the recordings' background noise first.
"false"consent*stringtrue (or 1, yes, on): the person agreed to the consent statement.
"true"consent_version?stringThe 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.
1 <= items <= 5The voice.
application/json- response
A voice of your organization's own.
{ "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*ClonedVoiceIdA cloned voice's own id (its voice_id, what a character takes, is another).
^vce_[0-9A-Za-z]{20}$"vce_3Hq8Wm1ZxT6kRb9NcV4p"voice_id*|What a character's voice_id takes; null until the voice is made.
name*string1 <= length <= 80description*stringlength <= 500labels*Words about the voice, each one line of at most 40 characters. Empty ones are dropped.
{ "accent": "Persian", "gender": "male"}status*stringcreating (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).
"creating""ready""needs_verification""failed"error*|Why it failed, in our words.
samples*integerHow many recordings it was made from.
character_ids*array<>The characters that speak with it.
consent*The consent record.
created_unix*UnixUnix seconds, UTC.
int641793300000updated_unix*UnixUnix seconds, UTC.
int641793300000curl -X POST 'https://api.daxov.com/v1/voices' \ -F 'name=string' \ -F 'consent=true' \ -F 'files=[ "string"]'{ "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}