# Stt

> Speech-to-text — transcribe voice to text using device microphone. Use for voice commands, dictation, or hands-free input. Use when this capability is needed.

- Skill: `tomevault-io/stt` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add tomevault-io/stt`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/stt/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tomevault-io (https://skillmd.com/u/tomevault-io)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/tomevault-io/stt

---


# Speech-to-Text

## Basic usage
```bash
termux-speech-to-text
```

Opens a speech recognition dialog. Returns transcribed text as JSON when user stops speaking.

## Output format
```json
{"result": "the spoken text here"}
```

## Notes
- Requires microphone permission
- Uses Google speech recognition (needs network)
- User must tap the mic or speak; dialog auto-closes on silence
- Returns empty result if canceled or no speech detected

---
> Converted and distributed by [TomeVault](https://tomevault.io/claim/mikeyobrien) — claim your Tome and manage your conversions.
<!-- tomevault:4.0:skill_md:2026-04-11 -->