# @desert-ant-labs/voz

> On-device speech recognition for JavaScript: transcripts with word-level timestamps, 25 languages. Runs in the browser on WebAssembly + ONNX Runtime Web (WebGPU, with the decode step on WebNN where the browser has it), and server-side in Node from one imp

Latest version **3.4.0** (published 2026-09-23) · SEE LICENSE IN LICENSE.md license · 0 weekly downloads

_The full health report (score, vulnerabilities, README, dependency tree, version history) is being computed; this document will grow once it lands._

## Install

```sh
npm install @desert-ant-labs/voz
pnpm add @desert-ant-labs/voz
yarn add @desert-ant-labs/voz
bun add @desert-ant-labs/voz
```

## Facts

| | |
|---|---|
| Version | 3.4.0 |
| Published | 2026-09-23 |
| First published | 2026-09-23 |
| Weekly downloads | 0 |
| License | SEE LICENSE IN LICENSE.md |
| TypeScript types | none |
| Dependencies | 0 |
| Maintainers | finnvoorhees, laurierrochon, pveugen, akagabi |
| Keywords | speech-recognition, asr, transcription, word-timestamps, subtitles, on-device, wasm, onnxruntime, webgpu, webnn, isomorphic |

## Links

- npm: https://www.npmjs.com/package/@desert-ant-labs/voz
- Repository: https://github.com/Desert-Ant-Labs/desert-ant-core
- Homepage: https://desertant.com/models/voz/
- npm.io page: https://npm.io/package/@desert-ant-labs/voz

---
_Source: https://npm.io/package/@desert-ant-labs/voz · Machine-readable twin of the npm.io package page. Health data is recomputed on every publish._