← 返回 Skills 市场
197
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install speech-translation
功能描述
Build, adapt, or run an audio-processing workflow that takes spoken audio, transcribes it with Whisper or faster-whisper, translates the transcript using the...
安全使用建议
This skill appears to do exactly what it says: local transcription, translation orchestration, and TTS. Before installing or running it: 1) Only configure notification command templates (or environment variables that set them) from trusted sources — the notifier code executes those commands with shell=True and may run arbitrary processes. 2) Prefer the provided mock senders for testing to avoid accidental data leaks. 3) Run the pipeline in a sandbox or isolated environment if you plan to use service backends or custom command hooks. 4) Validate any translation_service_url you provide and avoid pointing it to untrusted endpoints. 5) Keep the external piper binary and Python dependencies installed from trusted channels. If you want, I can point to the exact lines where subprocess.run with shell=True and unescaped formatting is used so you can review or harden them.
功能分析
Type: OpenClaw Skill
Name: speech-translation
Version: 1.0.0
The skill bundle contains multiple instances of potential command injection vulnerabilities where external commands are executed via `subprocess.run(..., shell=True)` using templates provided by environment variables or CLI arguments (specifically in `scripts/send_audio.py`, `scripts/send_text.py`, and `scripts/voice_translate_app/notifier.py`). While these are designed as notification hooks for the translation pipeline, the lack of strict validation on the command templates poses a significant RCE risk. However, the code logic and agent instructions in `SKILL.md` appear consistent with the stated purpose of audio processing and translation, with no clear evidence of intentional malice or data exfiltration.
能力评估
Purpose & Capability
The name/description match the included Python pipeline: transcription (faster-whisper or mock), translation (agent-LLM, manual, or HTTP service), and TTS (piper or mock). There are no unrelated required credentials, binaries, or config paths; the code and docs consistently implement the described workflows.
Instruction Scope
SKILL.md stays on-purpose (chat-native vs local pipeline, LLM-assisted default). It explicitly supports notification hooks that run external commands to report stages; those hooks (and send_text/send_audio helpers) cause the runtime to execute arbitrary shell commands when configured. This is expected for a pipeline but expands the skill's runtime actions beyond pure file IO/network calls — treat notification command templates as sensitive configuration.
Install Mechanism
No install spec (instruction-only + bundled scripts). That lowers risk because nothing is downloaded or installed by the registry; the repo only contains local Python scripts and shell wrappers. The runtime does require optional third-party packages (faster-whisper, requests) and an external 'piper' binary for full functionality, per the README.
Credentials
The skill declares no required env vars or credentials, which matches the code. However several scripts read optional environment variables (VOICE_TRANSLATE_TEXT_COMMAND_TEMPLATE, VOICE_TRANSLATE_AUDIO_COMMAND_TEMPLATE) as command templates. These are not required but, if set, control what external commands are run and could be used to exfiltrate data if misconfigured or supplied by an attacker.
Persistence & Privilege
The skill does not request persistent/always-on inclusion, does not modify other skills or system settings, and does not demand elevated privileges. It runs as a normal on-demand pipeline invoked by the agent/user.
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 speech-translation - 安装完成后，直接呼叫该 Skill 的名称或使用
/speech-translation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
v1.0.0
- Initial release of the voice translation skill.
- Supports audio transcription with Whisper or faster-whisper, translation by the current agent model, and speech synthesis using Piper, OpenClaw tts, or a mock backend.
- Offers two modes: chat-native voice translation and a deterministic local file-based pipeline.
- Ensures consistent output order: transcript, translation, then translated audio.
- Includes resources, references, and scripts for setup, orchestration, and backend selection.
- Designed for both interactive chat and automated batch workflows.
元数据
常见问题
speech-translation 是什么？
Build, adapt, or run an audio-processing workflow that takes spoken audio, transcribes it with Whisper or faster-whisper, translates the transcript using the... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 197 次。
如何安装 speech-translation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install speech-translation」即可一键安装，无需额外配置。
speech-translation 是免费的吗？
是的，speech-translation 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
speech-translation 支持哪些平台？
speech-translation 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 speech-translation？
由 decin（@decin）开发并维护，当前版本 v1.0.0。
推荐 Skills