A high-performance local speech-to-text skill utilizing whisper.cpp for fast, private, and GPU-accelerated audio transcription.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install local-whisper-cpp
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 local-whisper-cpp 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 Local Whisper (cpp)?
The Local Whisper (cpp) skill provides a robust solution for developers looking to integrate high-quality speech-to-text capabilities directly into their local environment. By leveraging whisper.cpp and the optimized large-v3-turbo model, it offers a privacy-first approach to transcription that avoids the latency and costs associated with cloud-based APIs. This is a vital addition to your collection of Openclaw Skills for handling sensitive audio data.
Designed for efficiency, this skill supports GPU acceleration to ensure that even large audio files are processed rapidly. It provides both a direct CLI interface and a convenient wrapper script, making it versatile for both manual use and automated background tasks.
Local Whisper (cpp) Use Cases
- Transcribing private meetings or voice memos without sending data to external servers.
- Batch processing audio archives for text-based indexing and search.
- Implementing voice-to-command functionality in local automation scripts.
- Generating subtitles for video content directly on a workstation.
How Local Whisper (cpp) Works
- The user initiates the transcription by passing an audio file path to the provided wrapper script or the whisper-cli binary.
- The system loads the ggml-large-v3-turbo model into memory, utilizing GPU resources for optimized processing.
- The audio is analyzed and transcribed using the whisper.cpp engine with automatic language detection.
- The resulting text is output to the console, allowing for immediate use or piping into other Openclaw Skills.
Local Whisper (cpp) Setup
Ensure you have whisper-cli installed on your system. To set up the required model, run the following commands:
sudo mkdir -p /usr/share/whisper.cpp-model-large-v3-turbo/
sudo wget https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo.bin?download=true -O /usr/share/whisper.cpp-model-large-v3-turbo/ggml-large-v3-turbo.bin
Local Whisper (cpp) Data Schema & Taxonomy
The skill manages model files and processes audio inputs as follows:
| Component | Details |
|---|---|
| Model Path | /usr/share/whisper.cpp-model-large-v3-turbo/ggml-large-v3-turbo.bin |
| Script Location | scripts/whisper-local.sh |
| Input Support | Standard audio formats compatible with whisper-cli |
| Output Format | Plain text transcription via stdout |
| Acceleration | GPU enabled by default via whisper-cli |
Local Whisper (cpp) Advanced Features
- Utilizes the large-v3-turbo model for the best balance of speed and transcription accuracy.
- Automatic language detection (-l auto) ensures seamless processing of multilingual audio.
- Support for GPU acceleration significantly reduces processing time for long recordings.
- Minimalist wrapper script allows for easy inclusion in complex DevOps or data pipelines.
SKILL.md
Loading
Related Openclaw Skills
Local Llama TTS
A high-performance local text-to-speech skill leveraging llama-tts and the OuteTTS-1.0-0.6B model for offline audio generation.
Xiaohongshu Note Creator
A comprehensive automation toolkit for generating professional Xiaohongshu notes, including copywriting, image card rendering, and automated publishing.
Retail Trade Weekly Report Generator
An automated tool for consolidating multi-channel retail sales data into comprehensive weekly performance reports with visual analytics.
WeChat Draft Publisher (mp-draft-push)
An automated workflow to publish formatted article content and cover images directly to the WeChat Official Account draft box.
AI Trend Monitor
A comprehensive monitoring tool for tracking AI market movements and technical breakthroughs across social and news channels.
CryptoTrading AI Agent
An autonomous AI-driven trading agent that executes data-backed crypto decisions every 10 minutes using dual-model verification and strict risk rules.
Featured*
