ボイスをローカライズする
Create a new voice from an existing voice localized to a new language and dialect.
承認
Cartesia API key (sk_car_...). Get one at play.cartesia.ai/keys.
ヘッダー
API version header.
2026-03-01 "2026-03-01"
ボディ
The ID of the voice to localize.
The name of the new localized voice.
A description for the voice, typically longer than the tagline if both are provided.
Target language to localize the voice to.
Options: English (en), German (de), Spanish (es), French (fr), Japanese (ja), Portuguese (pt), Chinese (zh), Hindi (hi), Italian (it), Korean (ko), Dutch (nl), Polish (pl), Russian (ru), Swedish (sv), Turkish (tr), Arabic (ar), Hebrew (he), Tamil (ta), Telugu (te), Thai (th).
en, de, es, fr, ja, pt, zh, hi, it, ko, nl, pl, ru, sv, tr, ar, he, ta, te, th male, female A few words describing the voice. At most 32 characters.
Accent for the localized voice. Must be valid for language.
This is a subset of the accents a voice can be tagged with: it lists only the accents localization can render. Omit to use the default accent for the language.
Modern Standard Arabic Who can access the localized voice.
Deprecated — use accent instead. accent covers every localizable language, while dialect is only supported for English (en), Spanish (es), Portuguese (pt), and French (fr).
To migrate, send the equivalent accent: Australian (au) → Australian English, British (uk) → British English, Indian (in) → Indian English, Southern (so) → Southern American English, American (us) → General American English, Latin American (mx) → Mexican Spanish, Peninsular (pe) → Castilian Spanish, Brazilian (br) → Brazilian Portuguese, European Portuguese (eu) → European Portuguese, Canadian (ca) → Canadian French, and Parisian/Metropolitan (eu) → Parisian French.
au, in, so, uk, us レスポンス
The ID of the voice. Find one in the Voice Library or via List Voices.
Who can access the voice
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"
Whether the voice is publicly accessible. Always false on this endpoint.
The ID of the user who owns the voice.