Skip to main content
POST
Batch Speech-to-Text

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
例:

"2026-08-14"

クエリパラメータ

encoding
enum<string> | null

Required when you upload raw PCM data without a container header. If you leave it out, the server decodes the audio automatically from its container, such as WAV, MP3, or FLAC. Must match the actual encoding of your audio. For detailed guidance on each format, see Audio Input.

利用可能なオプション:
pcm_s16le,
pcm_s32le,
pcm_f16le,
pcm_f32le,
pcm_mulaw,
pcm_alaw
sample_rate
integer | null

The sample rate of the audio in Hz, from 8000 to 48000

ボディ

multipart/form-data
file
file
必須

You don't need to split your audio file. The server splits long files into chunks for you.

Supported audio formats: flac, m4a, mp3, mp4, mpeg, mpga, oga, ogg, wav, webm

model
enum<string>
必須

ID of the model to use for transcription. Must be in the ink-whisper family of models.

利用可能なオプション:
ink-whisper
例:

"ink-whisper"

language
enum<string>
デフォルト:en

The language code of the input audio. If you leave it out, it defaults to en, and speech in other languages can come back translated into English.

利用可能なオプション:
en,
zh,
de,
es,
ru,
ko,
fr,
ja,
pt,
tr,
pl,
ca,
nl,
ar,
sv,
it,
id,
hi,
fi,
vi,
he,
uk,
el,
ms,
cs,
ro,
da,
hu,
ta,
no,
th,
ur,
hr,
bg,
lt,
la,
mi,
ml,
cy,
sk,
te,
fa,
lv,
bn,
sr,
az,
sl,
kn,
et,
mk,
br,
eu,
is,
hy,
ne,
mn,
bs,
kk,
sq,
sw,
gl,
mr,
pa,
si,
km,
sn,
yo,
so,
af,
oc,
ka,
be,
tg,
sd,
gu,
am,
yi,
lo,
uz,
fo,
ht,
ps,
tk,
nn,
mt,
sa,
lb,
my,
bo,
tl,
mg,
as,
tt,
haw,
ln,
ha,
ba,
jw,
su,
yue
timestamp_granularities[]
enum<string>[]

The granularity of timestamps to include in the response. Currently, only word is supported. It returns the start and end time of each word.

利用可能なオプション:
word

レスポンス

200 - application/json
type
enum<string>
必須

The message type. Always transcript for a batch transcription response.

利用可能なオプション:
transcript
text
string
必須

The transcribed text. A batch response is always the complete transcription.

request_id
string

Unique identifier for this transcription request

language
string

The specified language of the input audio

duration
number<double>

The duration of the input audio in seconds

words
TranscriptionWord · object[]

The start and end time of each word. Included only when you pass [word] in timestamp_granularities[].