Skip to main content
POST
Text-to-Speech (Bytes)

承認

Authorization
string
header
デフォルト:$CARTESIA_API_KEY
必須

Cartesia API key (sk_car_...). Get one at play.cartesia.ai/keys.

ヘッダー

Cartesia-Version
enum<string>
デフォルト:2026-08-14
必須

API version header.

利用可能なオプション:
2026-08-14
:

"2026-08-14"

ボディ

application/json
model_id
enum<string>
デフォルト:sonic-3.6
必須

The ID of the model to use for the generation. See Models all options.

利用可能なオプション:
sonic-3.6,
sonic-3.5,
sonic-3,
sonic-latest
:

"sonic-3.6"

transcript
string
デフォルト:Hi there, it's awesome to meet you.
必須
voice
必須

The ID of the voice.

:

"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4"

output_format
WAVOutputFormat · object
必須
language
string | null

The transcript's language or locale (for example en or en-GB). language and locale accept the same values. Set one or the other, never both; setting both returns a 400 error. See supported codes.

locale
string | null

The transcript's language or locale (for example en or en-GB). locale and language accept the same values. Set one or the other, never both; setting both returns a 400 error. See supported codes.

accent
string | null

Usually unnecessary: Cartesia picks the closest accent the voice supports for the requested language or locale. Set it only to make a multilingual voice sound accented (e.g. speak English with a French accent). Must come from the voice's Get Voice accents field. Learn more here.

normalization
string | null
デフォルト:auto

Text normalization. auto (default) runs the locale-aware normalizer, off skips it, or pass a language or locale code (for example en or en-IN) to pin the normalizer independently of the generation language. See Text Normalization.

pronunciation_dict_id
string | null

The ID of a pronunciation dictionary to use for the generation. Pronunciation dictionaries are supported by sonic-3 models and newer.

generation_config
GenerationConfig · object

Configure the various attributes of the generated speech. Available on sonic-3 and newer models; not available on earlier models.

See Volume, Speed, and Emotion for a guide on this option.

レスポンス

200 - audio/*

Audio bytes

The response is of type file.