# @moravianai/czechspeech

> Offline Czech speech-to-text for web apps: CzechSpeech (Whisper large-v3-turbo fine-tuned on Czech) on whisper.cpp in WebAssembly, on the GPU through WebGPU where available, with Silero VAD. Audio never leaves the page.

Latest version **0.3.0** (published 2026-11-19) · PolyForm-Noncommercial-1.0.0 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 @moravianai/czechspeech
pnpm add @moravianai/czechspeech
yarn add @moravianai/czechspeech
bun add @moravianai/czechspeech
```

## Facts

| | |
|---|---|
| Version | 0.3.0 |
| Published | 2026-11-19 |
| First published | 2026-11-19 |
| Weekly downloads | 0 |
| License | PolyForm-Noncommercial-1.0.0 |
| TypeScript types | bundled |
| Module format | ESM + CommonJS |
| Dependencies | 0 |
| Unpacked size | 21.3 MB |
| Author | Moravian AI |
| Maintainers | moravianai |
| Keywords | speech-to-text, speech-recognition, czech, cestina, whisper, whisper.cpp, webassembly, wasm, webgpu, vad, offline, on-device, privacy, browser |

## Links

- npm: https://www.npmjs.com/package/@moravianai/czechspeech
- Repository: https://github.com/moravian-ai/czechspeech-web
- Homepage: https://moravian.ai/czechspeech/
- npm.io page: https://npm.io/package/@moravianai/czechspeech

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