Assembling...
Enhanced Whisper pipeline adding word-level timestamps via forced alignment, voice activity detection for accurate segmentation, and speaker diarization. Significantly faster than vanilla Whisper through batched inference.
Transcript will appear here in real-time as you speak…
70x faster than vanilla Whisper through batched inference pipeline
Accurate word-level timestamps via phoneme-based forced alignment
Built-in speaker diarization labels who spoke each segment
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.
// WhisperX — Speech-to-Text
import { transcribe } from "@arkitekton/voice";
const result = await transcribe({
model: "vm-hf-002",
vendor: "huggingface",
audio: audioFile,
language: "en",
options: {
punctuate: true,
diarize: true,
smart_format: true,
},
});
console.log("Transcript:", result.text);
console.log("Confidence:", result.confidence);Community-driven open-source speech models and toolkits