Skip to content
TakoAPI
Back to skills

mh-openai-whisper

by mohdalhashemi98-hue

AI & LLMs
255Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Local speech-to-text with the Whisper CLI (no API key).

Description

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

INPUT

User asks: transcribe this interview recording to a text file

AGENT
  1. 1

    Identify the audio file path provided by the user

  2. 2

    Run whisper with --model medium, --output_format txt, and --output_dir set to current directory

  3. 3

    Wait for the model to download if not already cached

  4. 4

    Return the path to the generated .txt file

OUTPUT

interview.txt containing the full transcript

Installation

clawhub install mohdalhashemi98-hue/mh-openai-whisper

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links