ElevenLabs: Scribe v2 Realtime
elevenlabs/scribe-v2-realtime
active
stt
1 provider
ElevenLabs' realtime/streaming speech-to-text model for live and agentic use cases, with ~150ms latency and partial + committed transcripts.
AuthorElevenLabs
Languages1 languages
Statusactive
Providers
Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.
ProviderSlugPer hourLatencyiFor TTS, latency is measured as time to first byte of audio. For STT, latency is measured as time to first token.ModesUptime
ElevenLabs
3 params
elevenlabs
$0.39
—
Streaming
Supported languages
1 languages
English
en
Features
Speech to text
Transcribes spoken audio to text.
speech_to_text
Streaming
Real-time streaming transcription over WebSocket (~150ms latency).
streaming
Multilingual transcription
Supports over 90 languages.
multilingual_transcription
Word-level timestamps
Returns word-level timestamps for transcribed audio.
word_timestamps
Language detection
Automatically detects the spoken language.
language_detection
Code
ElevenLabs SDK streaming STT
Streams microphone or file audio through the ElevenLabs-compatible allmodels route.
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-v2-realtime",
languageCode: "en"
});
// Send audio frames to connection, then handle transcript events.