Speech to text
Scanned 9/5/2026
Install to Claude Code
npx -y skills add dvcrn/openclaw-skills-marketplace --skill stt --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Stt?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dvcrn-stt)More formats (shields.io, HTML) on the badges page.
---
name: stt
description: "Speech to text"
---
# Speech-to-Text (STT) Skill
Transcreve arquivos de áudio para texto usando OpenAI Whisper, otimizado para
português (Brasil).
## When to use
- Converter mensagens de voz ou áudios para texto
- Transcrever áudios do WhatsApp, Telegram, etc.
- Processar formatos: OGG, WAV, MP3, M4A, FLAC, AAC, OPUS
- Obter transcrições com timestamps
- Processar conteúdo em português brasileiro
## Tools
- stt_transcribe: Transcreve um arquivo de áudio específico
- stt_watch: Inicia monitoramento contínuo da pasta inbound
- stt_batch: Processa todos os áudios pendentes de uma vez
## Setup
1. **Instalar dependências:**
```bash
pip install -r requirements.txt
```
2. Instalar FFmpeg (necessário pelo Whisper):
- Windows: execute install_ffmpeg.cmd ou winget install "Gyan.FFmpeg"
- macOS: brew install ffmpeg
- Linux: sudo apt install ffmpeg
3. Criar pasta de entrada:
```bash
mkdir -p ../../../media/inbound
```
## Usage
### Transcrever arquivo específico
```bash
python stt_processor.py --file /caminho/para/audio.ogg
```
### Transcrever todos os áudios pendentes
```bash
python stt_processor.pyIs this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!