mh-openai-whisper
mohdalhashemi98-hue 제작
AI & LLMs요약
Local speech-to-text with the Whisper CLI (no API key).
설명
이 스킬이 하는 일
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.
사용 시점
- 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
예시 워크플로
User asks: transcribe this interview recording to a text file
- 1
Identify the audio file path provided by the user
- 2
Run whisper with --model medium, --output_format txt, and --output_dir set to current directory
- 3
Wait for the model to download if not already cached
- 4
Return the path to the generated .txt file
interview.txt containing the full transcript
설치
clawhub install mohdalhashemi98-hue/mh-openai-whisperCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.