技能/ #creative/ #Speech-to-Text

Openai Whisper

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

Peter Steinberger@steipete

安装

针对本地咔咔镜像运行此命令。

请从本地咔咔镜像安装 openai-whisper，注册表地址为 http://localhost:13001。安装后先检查 README、清单和权限，再在当前工作区使用。

下载

说明

--- name: openai-whisper description: Local speech-to-text with the Whisper CLI (no API key). homepage: https://openai.com/research/whisper metadata: {"clawdbot":{"emoji":"🎙️","requires":{"bins":["whisper"]},"install":[{"id":"brew","kind":"brew","formula":"openai-whisper","bins":["whisper"],"label":"Install OpenAI Whisper (brew)"}]}} ---

Whisper (CLI)

Use `whisper` to transcribe audio locally.

Quick start

`whisper /path/audio.mp3 --model medium --output_format txt --output_dir .`
`whisper /path/audio.m4a --task translate --output_format srt`

Notes

Models download to `~/.cache/whisper` on first run.
`--model` defaults to `turbo` on this install.
Use smaller models for speed, larger for accuracy.

安装解析

{
  "artifact": {
    "downloadUrl": "/api/v1/download?slug=openai-whisper&version=1.0.0&ownerHandle=steipete",
    "format": "zip",
    "generated": true,
    "kind": "skillArchive",
    "sha256": "cd06b8580e71fe4529746a385b9e1783f5f69c0002de833acf81fedd967d62a2",
    "size": 1857
  },
  "owner": {
    "displayName": "Peter Steinberger",
    "handle": "steipete",
    "id": "48a27aaa-8614-42e1-9ff1-7d7c299012b4",
    "verified": false
  },
  "skill": {
    "displayName": "Openai Whisper",
    "latestVersion": "1.0.0",
    "license": "unknown",
    "name": "openai-whisper",
    "ownerHandle": "steipete",
    "slug": "openai-whisper",
    "stats": {
      "downloads": 85731,
      "installs": 2966,
      "stars": 329
    },
    "summary": "Local speech-to-text with the Whisper CLI (no API key).",
    "tags": [
      "creative",
      "Speech-to-Text"
    ],
    "type": "skill",
    "updatedAt": "2026-07-06T10:48:37.017Z"
  },
  "sourceHandoff": null,
  "version": {
    "checksum": null,
    "checksumAlgorithm": null,
    "id": "aba71e0a-f00d-4917-8c81-06d21c88fcbe",
    "publishedAt": "2026-01-04T16:49:25.755Z",
    "size": null,
    "version": "1.0.0",
    "artifactStorageKey": null,
    "changelog": "",
    "manifest": {
      "clawhub": {
        "tags": {
          "latest": "1.0.0"
        },
        "owner": "steipete",
        "stats": {
          "stars": 329,
          "comments": 2,
          "installs": 2966,
          "versions": 1,
          "downloads": 85731
        },
        "topics": [
          "Speech-to-Text"
        ],
        "categories": [
          "creative"
        ]
      },
      "install": "openclaw skills install @steipete/openai-whisper"
    },
    "readme": "---\nname: openai-whisper\ndescription: Local speech-to-text with the Whisper CLI (no API key).\nhomepage: https://openai.com/research/whisper\nmetadata: {\"clawdbot\":{\"emoji\":\"🎙️\",\"requires\":{\"bins\":[\"whisper\"]},\"install\":[{\"id\":\"brew\",\"kind\":\"brew\",\"formula\":\"openai-whisper\",\"bins\":[\"whisper\"],\"label\":\"Install OpenAI Whisper (brew)\"}]}}\n---\n\n# Whisper (CLI)\n\nUse `whisper` to transcribe audio locally.\n\nQuick start\n- `whisper /path/audio.mp3 --model medium --output_format txt --output_dir .`\n- `whisper /path/audio.m4a --task translate --output_format srt`\n\nNotes\n- Models download to `~/.cache/whisper` on first run.\n- `--model` defaults to `turbo` on this install.\n- Use smaller models for speed, larger for accuracy.\n"
  }
}

版本

版本大小更新时间1.0.0暂无2026-01-04