Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
One-line agent install, keep-alive/on-demand loading, multi-language mix support, model upgrade guide
What This Skill Does
Runs a full AI inference stack locally on Apple Silicon Macs using the MLX framework. Covers LLM chat (Qwen3-14B, Gemma3-12B), speech-to-text via Whisper and Qwen3-ASR, text embeddings, OCR with PaddleOCR, and text-to-speech. All services expose OpenAI-compatible APIs on localhost.
Eliminates cloud API costs and keeps all data local while exposing the same OpenAI-compatible API format that most AI tooling already supports.
When to use it
- Transcribing Cantonese audio without uploading to cloud services
- Running privacy-sensitive LLM queries entirely on-device
- Extracting text from scanned documents or images via OCR
- Building local semantic search with on-device text embeddings
- Auto-transcribing a folder of meeting recordings in the background
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Transcribe and clean up the Cantonese meeting recording at ~/Downloads/meeting.m4a
- 1Copy meeting.m4a into ~/transcribe/ to trigger the daemon
- 2Daemon detects the file within 15 seconds and sends it to Qwen3-ASR on port 8788
- 3ASR output is saved as meeting_raw.md with the raw transcript
- 4Qwen3-14B reads the raw transcript, corrects homophones, adds punctuation, and preserves Cantonese characters
- 5Corrected file is moved to ~/transcribe/done/meeting_corrected.md
meeting_corrected.md in ~/transcribe/done/ with a clean, punctuated Cantonese transcript
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.