An AI-powered speech-to-text skill that utilizes OpenAI Whisper to transcribe audio files into accurate text automatically.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-skill-whisper-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 openclaw-skill-whisper-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 Whisper Speech-to-Text (STT)?
The whisper-stt skill is a robust transcription tool designed for the Openclaw Skills ecosystem. It utilizes OpenAI Whisper models to recognize and convert speech from various audio formats into high-quality text. Whether you are processing short voice memos or long recordings, this skill provides a seamless bridge between audio data and text-based workflows, ensuring that verbal information is easily captured and indexed.
By integrating this skill, users can benefit from state-of-the-art speech recognition that supports multiple languages, including excellent performance for Chinese. The skill is designed to run locally or on dedicated servers, providing privacy and flexibility in model selection to match your hardware capabilities.
Whisper Speech-to-Text (STT) Use Cases
- Automatically transcribing voice messages received in communication apps like Feishu.
- Converting recorded meetings or interviews into text for documentation and searchability.
- Generating transcripts for podcasts or video content to improve accessibility.
- Transforming voice memos into written tasks or notes within a productivity system.
How Whisper Speech-to-Text (STT) Works
- The user provides an audio file or sends a voice message to the agent.
- The Openclaw Skills framework detects the audio input and invokes the whisper-stt engine.
- The skill utilizes FFmpeg to process the audio stream into a compatible format.
- The selected Whisper model (e.g., base, turbo, or large) performs the transcription process.
- The identified text is extracted and returned to the user or forwarded to a designated platform like Feishu.
Whisper Speech-to-Text (STT) Setup
To use this skill within Openclaw Skills, you must ensure your environment meets the hardware and software requirements. Use the following commands to set up the environment:
# Install system dependencies (FFmpeg is required)
sudo apt update && sudo apt install ffmpeg
# Install Python dependencies
pip install openai-whisper torch
Upon first execution, the skill will automatically download the specified Whisper model, which can range from 1GB to 10GB depending on the version selected.
Whisper Speech-to-Text (STT) Data Schema & Taxonomy
The whisper-stt skill handles various audio inputs and produces structured text outputs. Below is the technical specification for data handling:
| Attribute | Details |
|---|---|
| Input Formats | MP3, WAV, M4A, OGG, FLAC, WebM (Any FFmpeg supported format) |
| Model Selection | tiny, base, small, medium, large, turbo |
| Output Data | Plain text transcriptions |
| Accuracy | Scalable based on model size (Large/Turbo offering highest precision) |
| Memory Requirement | 1GB (tiny) up to 10GB+ (large) |
Whisper Speech-to-Text (STT) Advanced Features
- Support for Whisper Turbo, offering a balance of high speed and near-large model accuracy.
- Seamless integration with Feishu for automated message-to-text forwarding.
- Multi-format support via FFmpeg integration for universal audio compatibility.
- Automatic language detection and high-performance transcription for Chinese and English.
- Configurable model tiers to optimize performance based on available GPU or RAM resources.
SKILL.md
Loading
Related Openclaw Skills
Session Memory Skill
A skill that automatically archives AI conversations into dated Markdown files while masking sensitive data for secure retrieval.
MiniMax Usage Tracker
A dedicated tracking tool for monitoring and managing MiniMax API prompt consumption in real-time.
cutmv Video Tool
A high-performance media processing utility for video cutting, compression, and format conversion powered by FFmpeg.
cutmv Video Tool
A comprehensive FFmpeg-based video utility for cutting, compressing, and converting media files within AI agent workflows.
Dream of Clawra
An automated media-sharing skill that selects and sends contextually relevant images and dance videos to messaging channels via OpenClaw.
IP Lookup
A network utility skill for retrieving public IP addresses and detailed geolocation information via CLI commands.
Featured*
