Zum Inhalt springen
TakoAPI
Zurück zu den Skills

mh-openai-whisper

von mohdalhashemi98-hue

AI & LLMs
255Downloadzahlen laut clawskills.sh
0Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

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

Beschreibung

Was dieser Skill macht

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.

Wann du ihn einsetzt

  • 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

Beispiel-Workflow

EINGABE

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

AUSGABE

interview.txt containing the full transcript

Installation

clawhub install mohdalhashemi98-hue/mh-openai-whisper

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links