본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

mh-openai-whisper-api

mohdalhashemi98-hue 제작

AI & LLMs
235clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

설명

이 스킬이 하는 일

Transcribes audio files by sending them to OpenAI's Whisper API endpoint. Supports multiple audio formats, language hints, speaker prompts, and JSON or plain text output.

Uses OpenAI's hosted Whisper model via a single curl call, so no local model setup or GPU is needed.

사용 시점

  • Transcribing recorded meetings or interviews
  • Converting voice memos to text
  • Generating subtitles from audio clips
  • Transcribing podcast episodes
  • Extracting text from language learning recordings

예시 워크플로

입력

User asks: transcribe my interview recording at /recordings/interview.m4a with speaker names Peter and Daniel

에이전트
  1. 1

    Receives audio file path and speaker context

  2. 2

    Calls transcribe.sh with --prompt flag set to 'Speaker names: Peter, Daniel'

  3. 3

    Sends multipart form request to /v1/audio/transcriptions with whisper-1 model

  4. 4

    Writes transcript to interview.m4a.txt in the same directory

출력

Plain text transcript saved to /recordings/interview.m4a.txt

요구 사항

  • OPENAI_API_KEY environment variable

설치

clawhub install mohdalhashemi98-hue/mh-openai-whisper-api

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크