Conçu pour les agents vocaux qui ne peuvent pas attendre 600ms

ElevenLabs : Scribe v3

elevenlabs/scribe-v3
actif stt 1 fournisseur
Playground

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.

AuteurElevenLabs
Langues100 langues
Statutactif

Fournisseurs

Plusieurs fournisseurs peuvent héberger le même modèle. Choisissez-en un lorsque vous avez besoin d’un backend fixe, ou laissez le routage choisir parmi eux.

FournisseurSlugPar heureLatenceiPour le TTS, la latence correspond au délai jusqu’au premier octet audio. Pour le STT, elle correspond au délai jusqu’au premier token.ModesDisponibilité
ElevenLabs 7 paramètres
elevenlabs
À partir de $0,2
—
Synchrone

Langues prises en charge

100 langues
Afrikaans af
Amharic am
Arabic ar
Armenian hy
Assamese as
Asturian ast
Azerbaijani az
Belarusian be
Bengali bn
Bosnian bs
Bulgarian bg
Burmese my
Cantonese yue
Catalan ca
Cebuano ceb
Chichewa ny
Croatian hr
Czech cs
Danish da
Dutch nl
English en
Estonian et
Filipino fil
Finnish fi
French fr
Fulah ff
Galician gl
Ganda lg
Georgian ka
German de
Greek el
Gujarati gu
Hausa ha
Hebrew he
Hindi hi
Hungarian hu
Icelandic is
Igbo ig
Indonesian id
Irish ga
Italian it
Japanese ja
Javanese jv
Kabuverdianu kea
Kannada kn
Kazakh kk
Khmer km
Korean ko
Kurdish ku
Kyrgyz ky
Lao lo
Latvian lv
Lingala ln
Lithuanian lt
Luo luo
Luxembourgish lb
Macedonian mk
Malay ms
Malayalam ml
Maltese mt
Mandarin Chinese zh
Māori mi
Marathi mr
Mongolian mn
Nepali ne
Northern Sotho nso
Norwegian no
Occitan oc
Odia or
Pashto ps
Persian fa
Polish pl
Portuguese pt
Punjabi pa
Romanian ro
Russian ru
Serbian sr
Shona sn
Sindhi sd
Sinhala si
Slovak sk
Slovenian sl
Somali so
Spanish es
Swahili sw
Swedish sv
Tamil ta
Tajik tg
Telugu te
Thai th
Turkish tr
Ukrainian uk
Umbundu umb
Urdu ur
Uzbek uz
Vietnamese vi
Welsh cy
Wolof wo
Xhosa xh
Zulu zu

Fonctionnalités

Speech to text

Transcribes spoken audio to text.

speech_to_text
Synchronous

Transcribes a fully-submitted audio file in a single synchronous request via the /v1/speech-to-text endpoint.

synchronous
Multilingual transcription

Supports 90+ languages, with secondary language codes for mixed-language audio.

multilingual_transcription
Word-level timestamps

Returns word-level timestamps for transcribed audio.

word_timestamps
Language detection

Automatically detects the spoken language.

language_detection
Speaker diarization

Identifies and labels multiple speakers (up to 32).

speaker_diarization
Keyterm prompting

Biases recognition toward up to 1,000 supplied keyterms (50 characters each).

keyterm_prompting
Entity detection

Detects and optionally redacts sensitive entities such as PII, PHI and PCI with timestamps.

entity_detection

Code

Client
Mode
Langage

STT en streaming avec l’ElevenLabs SDK

Diffuse l’audio du micro ou d’un fichier via la route AllModels compatible 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.