Assembling...
End-to-end CTC-based ASR model family optimized for high accuracy and low footprint. Available in multiple sizes from 0.6B to 1.8B parameters, achieving state-of-the-art word error rates on common benchmarks.
Transcript will appear here in real-time as you speak…
State-of-the-art English WER across LibriSpeech and other benchmarks
Compact CTC architecture enables efficient edge deployment
Open-source Apache 2.0 with NeMo toolkit integration
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.
// Parakeet — Speech-to-Text
import { transcribe } from "@arkitekton/voice";
const result = await transcribe({
model: "vm-nv-005",
vendor: "nvidia",
audio: audioFile,
language: "en",
options: {
punctuate: true,
diarize: true,
smart_format: true,
},
});
console.log("Transcript:", result.text);
console.log("Confidence:", result.confidence);GPU-accelerated speech AI and conversational frameworks