Saltar al contenido
TakoAPI
Volver a skills

mh-openai-whisper

por mohdalhashemi98-hue

AI & LLMs
255Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

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

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

User asks: transcribe this interview recording to a text file

AGENTE
  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

SALIDA

interview.txt containing the full transcript

Instalación

clawhub install mohdalhashemi98-hue/mh-openai-whisper

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces