← 返回 Skills 市场
Whisper AI Audio to Text Transcriber
作者
babybabyyeah
· GitHub ↗
· v1.0.1
· MIT-0
437
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install whisper-audio-transcription
功能描述
Turn raw transcripts into structured summaries, meeting minutes, and action items.
安全使用建议
This skill appears to be a transcript summarizer, not an audio-to-text transcriber despite its name. Before installing or using it: (1) Confirm you understand it will not convert audio to text — you must provide the transcript. (2) If you expected automatic transcription, ask the author for code or instructions that call a transcription model (e.g., Whisper, an API) and note any credentials that would be required. (3) Be cautious about uploading sensitive transcripts: summarization will send the transcript content to the model provider when the agent processes it. If confidentiality is required, prefer a skill that explicitly documents local/offline transcription or shows how it handles credentials and data. (4) The skill has no source/homepage listed — consider requesting source code or a trustworthy origin before relying on it.
功能分析
Type: OpenClaw Skill
Name: whisper-audio-transcription
Version: 1.0.1
The skill bundle consists of metadata and Markdown instructions for an AI agent to summarize transcripts into meeting notes and action items. There is no executable code, and the instructions in SKILL.md are focused entirely on text processing and formatting without any signs of prompt injection, data exfiltration, or malicious intent.
能力评估
Purpose & Capability
The skill is named 'Whisper AI Audio to Text Transcriber' but the SKILL.md contains only instructions for summarizing/structuring an existing transcript and does not include any transcription steps, required binaries, or credentials for a transcription service. This mismatch could mislead users who expect automatic audio transcription.
Instruction Scope
The runtime instructions stay within the stated summarization task: cleaning transcript text, extracting topics/decisions/action items, and producing structured notes. They do not request arbitrary files, extra env vars, or external endpoints. The SKILL.md explicitly requires the user to provide a transcript.
Install Mechanism
No install spec or code files are present (instruction-only), so nothing will be written to disk or installed during setup.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate to the summarization-only instructions provided.
Persistence & Privilege
The skill is not always-enabled and has normal agent invocation settings. It does not request persistent privileges or modify other skills.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install whisper-audio-transcription - 安装完成后,直接呼叫该 Skill 的名称或使用
/whisper-audio-transcription触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
Initial release.
Adds a skill that converts raw transcripts into structured summaries,
meeting notes, decisions, and action items.
v1.0.0
Initial release of Whisper transcription assistant skill.
元数据
常见问题
Whisper AI Audio to Text Transcriber 是什么?
Turn raw transcripts into structured summaries, meeting minutes, and action items. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 437 次。
如何安装 Whisper AI Audio to Text Transcriber?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install whisper-audio-transcription」即可一键安装,无需额外配置。
Whisper AI Audio to Text Transcriber 是免费的吗?
是的,Whisper AI Audio to Text Transcriber 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Whisper AI Audio to Text Transcriber 支持哪些平台?
Whisper AI Audio to Text Transcriber 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Whisper AI Audio to Text Transcriber?
由 babybabyyeah(@yvette1226)开发并维护,当前版本 v1.0.1。
推荐 Skills