Clone Voice
Authorizations
Cartesia API key (sk_car_...). Get one at play.cartesia.ai/keys.
Headers
API version header.
2026-08-14 "2026-08-14"
Body
See Clone Voices for guidance on choosing a clip.
Supported audio formats: flac, mp3, mpeg, mpga, oga, ogg, wav, webm
The name of the voice.
The language of the voice.
en, fr, de, es, pt, zh, ja, hi, it, ko, nl, pl, ru, sv, tr, tl, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, hu, no, vi, bn, th, he, ka, id, te, gu, kn, ml, mr, pa, or, ur A few words describing the voice. At most 32 characters.
A description for the voice, typically longer than the tagline if both are provided.
Optional catalog accent id from GET /accents (e.g. southern-us). Must be valid for language. Omit to leave unset. Display names are rejected.
arabic, khaleeji, middle-eastern-arabic, modern-standard-arabic Optional base voice ID that the cloned voice is derived from.
Who can use the cloned voice. Prefer "public" | "private". Deprecated form field access[type] is still accepted.
private, public Response
The ID of the voice. Find one in the Voice Library or via List Voices.
Who can use the resource. private means only the owner can use the resource. public means everyone can use the resource.
private, public The name of the voice.
A few words describing the voice.
A description for the voice, typically longer than the tagline if both are provided.
The date and time the voice was created.
The voice's language, as an ISO 639-1 code (e.g. en, fr, zh)
"en"
The ID of the user who owns the voice.
When the resource is returned by the list endpoint. owner means the resource appears for the owner only. all means the resource appears for all users.
owner, all