A high-performance audio processing utility that leverages OpenAI Whisper to convert diverse audio formats into accurate text transcriptions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install stt
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install stt using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Speech-to-Text (STT) Skill?
The Speech-to-Text (STT) Skill is a professional-grade transcription tool built to handle the complexities of modern audio processing. By integrating the OpenAI Whisper model, this skill delivers high-fidelity text output from various voice sources, specifically optimized for Portuguese (Brazil). As a core component within the library of Openclaw Skills, it provides a seamless bridge between spoken content and actionable text data.
Whether you are processing personal voice notes or managing large-scale media archives, this skill simplifies the workflow by automating the transcription lifecycle. It is designed to be lightweight, efficient, and easily integrated into broader automation pipelines that require reliable speech recognition.
Speech-to-Text (STT) Skill Use Cases
- Transcribing voice messages from messaging apps like WhatsApp or Telegram.
- Converting recorded meetings or lectures into searchable text documents.
- Extracting content from various audio formats including OGG, WAV, MP3, and M4A.
- Generating time-stamped transcriptions for media indexing and accessibility.
- Batch processing legacy audio archives for digital documentation.
How Speech-to-Text (STT) Skill Works
- The skill monitors a designated inbound directory or accepts a direct file path for audio input.
- It utilizes FFmpeg to ensure the audio stream is compatible with the transcription engine.
- The OpenAI Whisper model processes the audio data to identify speech patterns and convert them to text.
- Timestamps and metadata are generated alongside the transcription for precise content mapping.
- The final output is delivered via the CLI or saved to the filesystem, making it ready for other Openclaw Skills to consume.
Speech-to-Text (STT) Skill Setup
- Install the required Python dependencies:
pip install -r requirements.txt
- Install FFmpeg, which is required by Whisper for audio decoding:
- Windows: Run
install_ffmpeg.cmdor usewinget install "Gyan.FFmpeg" - macOS:
brew install ffmpeg - Linux:
sudo apt install ffmpeg
- Initialize the inbound directory structure:
mkdir -p ../../../media/inbound
Speech-to-Text (STT) Skill Data Schema & Taxonomy
| Data Component | Specification |
|---|---|
| Supported Formats | OGG, WAV, MP3, M4A, FLAC, AAC, OPUS |
| Processing Engine | OpenAI Whisper |
| Inbound Path | media/inbound |
| Output Type | Text with metadata and optional timestamps |
| Target Language | Optimized for Portuguese (Brazil) |
Speech-to-Text (STT) Skill Advanced Features
- Continuous monitoring mode using the watch tool for real-time file processing.
- Batch execution capabilities to process multiple pending audio files in a single pass.
- Support for a wide array of modern audio codecs without manual conversion.
- Easy integration with other Openclaw Skills for automated content workflows.
SKILL.md
Loading
Related Openclaw Skills
Strava
A comprehensive integration for loading, analyzing, and tracking Strava fitness activities and athlete performance data.
Vector Robot Controller
A comprehensive toolset for programmatic control and voice integration of Anki Vector robots via the wire-pod server.
Tenzing Moltbook Skill
Tenzing is an autonomous assistant designed to distill complex information, organize workspaces, and facilitate multi-agent collaboration.
agent-browser
A headless browser automation CLI designed for AI agents to navigate, interact with, and extract data from websites seamlessly.
Colormind
A technical tool for generating professional color palettes and extracting color schemes from images via the Colormind.io API.
Modular Market Brief
A configurable AI skill for generating modular, data-driven global market briefs across equities, crypto, and commodities.
Featured*
