跳到正文
TakoAPI
返回技能列表

mh-openai-whisper-api

由 mohdalhashemi98-hue 提供

AI & LLMs
235下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

描述

该技能的功能

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.

何时使用

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

示例工作流

输入

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

智能体
  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

输出

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

前置要求

  • OPENAI_API_KEY environment variable

安装

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

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接