ElevenLabs: Scribe v3 Live
ElevenLabs' most accurate realtime/streaming speech-to-text model for voice agents and live captioning, succeeding Scribe v2 Realtime with 43% fewer errors, realtime diarization, turn prediction and multilingual mode.
プロバイダー
同じモデルを複数のプロバイダーがホストしている場合があります。バックエンドを固定したい場合は1つのプロバイダーを選び、そうでなければルーティングに選択を任せられます。
対応言語
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
機能
Transcribes spoken audio to text.
speech_to_text
Real-time streaming transcription over WebSocket.
streaming
Supports 90+ languages, with a multilingual mode that follows mid-sentence language switches.
multilingual_transcription
Returns word-level timestamps for transcribed audio.
word_timestamps
Automatically detects the spoken language.
language_detection
Labels speakers in realtime via diarize=true: a speaker-labelled transcript for each committed segment, plus notices when two speaker labels are merged.
speaker_diarization
The turn_prediction commit strategy commits when the speaker is predicted to have finished; the client still commits any trailing audio after it stops sending.
turn_detection
Biases recognition toward up to 50 keyterms (20 characters each) per session, or a keyterm library sent with the first audio chunk.
keyterm_prompting
Detects entities in realtime transcripts and can return a redacted copy of each committed segment; partial and committed transcripts keep the original text.
entity_detection
コード
ElevenLabs SDKでのストリーミングSTT
マイクまたはファイルの音声を、ElevenLabs互換のAllModelsルート経由でストリーミングします。
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-live",
languageCode: "en"
});
// Send audio frames to connection, then handle transcript events.
