Assembling...
Compact 3B-parameter ASR model optimized for edge and local deployment. Achieves strong multilingual accuracy at a fraction of the compute cost of larger models, making it viable for on-device and embedded use cases.
Transcript will appear here in real-time as you speak…
3B parameters enable real-time transcription on consumer hardware
Strong multilingual accuracy despite compact model size
Quantization-friendly architecture for INT4/INT8 edge deployment
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 Mini 3B — Speech-to-Text
import { transcribe } from "@arkitekton/voice";
const result = await transcribe({
model: "vm-mst-002",
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