跳到正文
TakoAPI
返回技能列表

mh-openai-whisper

由 mohdalhashemi98-hue 提供

AI & LLMs
255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

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

描述

该技能的功能

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.

何时使用

  • 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

示例工作流

输入

User asks: transcribe this interview recording to a text file

智能体
  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

输出

interview.txt containing the full transcript

安装

clawhub install mohdalhashemi98-hue/mh-openai-whisper

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