ElevenLabs: Scribe v3
ElevenLabs' most accurate synchronous speech-to-text model for prerecorded/file transcription, succeeding Scribe v2 with 27% fewer word errors, speaker diarization and keyterm prompting across the 90+ language Scribe catalog.
Proveedores
Distintos proveedores pueden alojar el mismo modelo. Elige un proveedor cuando necesites un backend fijo, o deja que el enrutamiento elija entre ellos.
Idiomas admitidos
af
am
ar
hy
as
ast
az
be
bn
bs
bg
my
yue
ca
ceb
ny
hr
cs
da
nl
en
et
fil
fi
fr
ff
gl
lg
ka
de
el
gu
ha
he
hi
hu
is
ig
id
ga
it
ja
jv
kea
kn
kk
km
ko
ku
ky
lo
lv
ln
lt
luo
lb
mk
ms
ml
mt
zh
mi
mr
mn
ne
nso
no
oc
or
ps
fa
pl
pt
pa
ro
ru
sr
sn
sd
si
sk
sl
so
es
sw
sv
ta
tg
te
th
tr
uk
umb
ur
uz
vi
cy
wo
xh
zu
Funciones
Transcribes spoken audio to text.
speech_to_text
Transcribes a fully-submitted audio file in a single synchronous request via the /v1/speech-to-text endpoint.
synchronous
Supports 90+ languages, with secondary language codes for mixed-language audio.
multilingual_transcription
Returns word-level timestamps for transcribed audio.
word_timestamps
Automatically detects the spoken language.
language_detection
Identifies and labels multiple speakers (up to 32).
speaker_diarization
Biases recognition toward up to 1,000 supplied keyterms (50 characters each).
keyterm_prompting
Detects and optionally redacts sensitive entities such as PII, PHI and PCI with timestamps.
entity_detection
Código
STT en streaming con el ElevenLabs SDK
Transmite audio del micrófono o de un archivo a través de la ruta de AllModels compatible con ElevenLabs.
import { ElevenLabsClient } from "elevenlabs";
const client = new ElevenLabsClient({
apiKey: process.env.ALLMODELS_API_KEY,
baseUrl: "https://api.allmodels.io/el"
});
const connection = await client.speechToText.realtime.connect({
modelId: "elevenlabs/scribe-v3",
languageCode: "en"
});
// Send audio frames to connection, then handle transcript events.
