Assembling...
Ultra-low-latency live transcription model from Mistral optimized for real-time applications. Streams transcription results with minimal delay, supporting live captioning, call center analytics, and real-time translation pipelines.
Transcript will appear here in real-time as you speak…
Sub-150ms latency purpose-built for live captioning and analytics
Streaming-first architecture eliminates buffering delays
Integrates into real-time translation and analytics pipelines
Transcribe meetings in real-time with speaker identification and punctuation.
Analyze customer calls at scale with sentiment detection and keyword spotting.
Convert audio and video libraries into searchable text archives.
Provide real-time captions for broadcasts, presentations, and live events.
// Voxtral Realtime — Speech-to-Text
import { transcribe } from "@arkitekton/voice";
const result = await transcribe({
model: "vm-mst-003",
vendor: "mistral",
audio: audioFile,
language: "en",
options: {
punctuate: true,
diarize: true,
smart_format: true,
},
});
console.log("Transcript:", result.text);
console.log("Confidence:", result.confidence);Open-weight multilingual speech models from Europe