Stats
Actions
Tags
From transcription
Use when the user wants to transcribe audio files (MP3, WAV, M4A) to text using MLX Whisper on Apple Silicon
How this skill is triggered — by the user, by Claude, or both
Slash command
/transcription:transcriptionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Fast local transcription using MLX Whisper with Apple Silicon GPU/Neural Engine acceleration.
Fast local transcription using MLX Whisper with Apple Silicon GPU/Neural Engine acceleration.
The script at ${CLAUDE_PLUGIN_ROOT}/scripts/transcribe.py processes MP3/WAV/M4A files:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/transcribe.py /path/to/audio/files/
python3 -m venv .venv
source .venv/bin/activate
pip install mlx-whisper
npx claudepluginhub varunr89/claude-marketplace --plugin transcriptionTranscribes local audio/video files to Markdown and SRT subtitles using MLX/Whisper (Apple Silicon) or faster-whisper (others).
Switches voice transcription from OpenAI Whisper API to local whisper.cpp on Apple Silicon. Currently WhatsApp-only. Requires voice-transcription skill first.
Switches voice transcription from OpenAI Whisper API to local whisper.cpp on Apple Silicon for WhatsApp channels. On-device, no network or API key needed.