Setup & Installation
openclaw skills install @mohdalhashemi98-hue/mh-openai-whisper
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install mh-openai-whisper
What This Skill Does
Runs OpenAI's Whisper speech recognition model locally via the command line. Transcribes or translates audio files to text without sending data to any external API. Models are cached locally after the first download.
Runs entirely on-device, so audio never leaves your machine and there are no per-request API costs.
When to use it
- Transcribing recorded meeting audio to a text file
- Generating SRT subtitle files for video content
- Translating foreign-language audio directly to English text
- Batch transcribing voice memos offline
- Converting podcast episodes to searchable text
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: transcribe this interview recording to a text file
AGENT
- 1Identify the audio file path provided by the user
- 2Run whisper with --model medium, --output_format txt, and --output_dir set to current directory
- 3Wait for the model to download if not already cached
- 4Return the path to the generated .txt file
OUTPUT
interview.txt containing the full transcript