# Voice2text

> slug: voice2text title: Voice to Text description: Offline speech-to-text skill using Vosk local model. author: lxxtad license: MIT

- Skill: `modbender/voice2text` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add modbender/voice2text`
- Raw SKILL.md: https://api.skillmd.com/api/skills/modbender/voice2text/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: modbender (https://skillmd.com/u/modbender)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/modbender/voice2text

---


# voice2text

slug: voice2text
title: Voice to Text
description: Offline speech-to-text skill using Vosk local model.
author: lxxtad
license: MIT

**入口**: `main.py` implements `run(params)` – pass `{"audio":"path/to.wav"}` and get `{"text":"transcript"}`.

**依赖**: `vosk`, `pytest`.

**使用示例**:
```bash
clawhub install voice2text
clawhub run voice2text '{"audio":"sample.wav"}'
```