Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

Comenzar

openai-whisper-api

Estrellas5

Forks0

Actualizado24 de marzo de 2026 a las 10:15

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

HikariShine

HikariShine/AgentStudy

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

2 archivos

SKILL.md

readonly

name	openai-whisper-api
description	Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
homepage	https://platform.openai.com/docs/guides/speech-to-text
metadata	{"openclaw":{"emoji":"☁️","requires":{"bins":["curl"],"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"}}

OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.

Quick start

{baseDir}/scripts/transcribe.sh /path/to/audio.m4a

Defaults:

Model: whisper-1
Output: <input>.txt

Useful flags

{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json

API key & Base URL

Set OPENAI_API_KEY and OPENAI_BASE_URL, or configure it in ~/.openclaw/openclaw.json:

{
  skills: {
    "openai-whisper-api": {
      env: {
        OPENAI_API_KEY: "OPENAI_KEY_HERE",
        OPENAI_BASE_URL: "http://your-proxy:3000" // Optional, default: https://api.openai.com
      }
    }
  }
}

Más de este repositorio

mismo repositorio

stock-chooser

HikariShine/AgentStudy

选股技能，用户希望研究任意下游行业扩产时，其上游供给端（材料、设备、零部件等）的核心受益标的。

2026-05-215

biliup-skills

HikariShine/AgentStudy

使用命令行工具 biliup（Python 版官方 CLI，非 biliup-rs）向 B 站（bilibili）投稿视频。触发场景：用户说"投稿 B 站"、"上传到 B 站"、"发 B 站"、"bilibili 投稿"、"B 站发视频"、"上传视频到 bilibili"等相关关键字。功能：(1) 自动检测并通过 uv 安装 biliup，(2) 浏览器扫码登录并发送二维码图片给用户，(3) 收集视频信息后执行投稿，(4) 返回投稿结果。

2026-03-275

my-wechat-publish

HikariShine/AgentStudy

个人微信公众号文章生成与发布。当需要生成并发布微信公众号到文章草稿箱时使用。

2026-03-255

daily-report

HikariShine/AgentStudy

Generate daily work report for ShineClaw project.

2026-03-245

nano-banana-pro

HikariShine/AgentStudy

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

2026-03-245

openai-image-gen

HikariShine/AgentStudy

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

2026-03-245

name	openai-whisper-api
description	Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
homepage	https://platform.openai.com/docs/guides/speech-to-text
metadata	{"openclaw":{"emoji":"☁️","requires":{"bins":["curl"],"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"}}

OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.

Quick start

{baseDir}/scripts/transcribe.sh /path/to/audio.m4a

Defaults:

Model: whisper-1
Output: <input>.txt

Useful flags

{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json

API key & Base URL

Set OPENAI_API_KEY and OPENAI_BASE_URL, or configure it in ~/.openclaw/openclaw.json:

{
  skills: {
    "openai-whisper-api": {
      env: {
        OPENAI_API_KEY: "OPENAI_KEY_HERE",
        OPENAI_BASE_URL: "http://your-proxy:3000" // Optional, default: https://api.openai.com
      }
    }
  }
}