Pular para o conteúdo
TakoAPI
Voltar às skills

mh-openai-whisper-api

por mohdalhashemi98-hue

AI & LLMs
235Downloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Descrição

O que esta skill faz

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.

Quando usá-la

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

Exemplo de fluxo de trabalho

ENTRADA

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

AGENTE
  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

SAÍDA

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

Requisitos

  • OPENAI_API_KEY environment variable

Instalação

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

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links