← 返回 Skills 市场
Voice messaging setup
作者
Dmitry Aksenkin
· GitHub ↗
· v1.0.3
498
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install voice-stt-tts
功能描述
Full voice message setup (STT + TTS) for OpenClaw using faster-whisper and Edge TTS
安全使用建议
This skill appears to do what it claims, but before running: (1) review and back up ~/.openclaw/openclaw.json — the instructions modify it; (2) expect pip to install large/native packages (onnxruntime, ctranslate2, ffmpeg may be needed) and for faster-whisper to download model weights from the Hugging Face hub (large disk and network usage); (3) prefer running the install steps manually in a terminal so you can inspect outputs and resolve missing system packages; (4) confirm the TTS 'edge' provider behavior in your OpenClaw environment (some providers may still call external services); (5) if you have security or bandwidth constraints, run this in an isolated machine or container. If you want me to, I can (a) extract the exact file changes the SKILL.md will make, (b) produce step-by-step shell commands you can run interactively, or (c) list additional system packages you may need (ffmpeg, build tools) for faster-whisper to install successfully.
功能分析
Type: OpenClaw Skill
Name: voice-stt-tts
Version: 1.0.3
The OpenClaw AgentSkills bundle 'voice-stt-tts' is designed to set up Speech-to-Text (STT) and Text-to-Speech (TTS) capabilities. It installs the legitimate `faster-whisper` Python library in a virtual environment and creates a `transcribe.py` script, both via `bash` commands embedded in `SKILL.md`. The script itself is straightforward, processing audio files for transcription without any suspicious system calls or network activity. The configuration instructions for OpenClaw are standard for integrating such a service. There is no evidence of data exfiltration, persistence mechanisms, unauthorized remote control, or prompt injection attempts against the agent to perform malicious actions. The use of `{{MediaPath}}` as an argument placeholder is standard for OpenClaw and does not indicate malicious intent from this skill, though it highlights a general platform vulnerability if argument sanitization is insufficient.
能力评估
Purpose & Capability
The name/description (STT + TTS using faster-whisper and Edge TTS) match the actions in SKILL.md: creating a venv, installing faster-whisper, creating a transcribe.py, and adding OpenClaw config entries for media.audio and messages.tts. Nothing requested or shown is unrelated to providing local transcription and TTS.
Instruction Scope
The instructions direct the agent to create files under ~/.openclaw/workspace/voice-messages, install packages into that venv, and modify ~/.openclaw/openclaw.json. These actions are expected for this purpose, but they do write to the user's home and update OpenClaw config — the user should review/backup that config before applying changes. The SKILL.md does not explicitly warn that model weights will be downloaded at runtime (faster-whisper/huggingface-hub), which is an important runtime behavior to be aware of.
Install Mechanism
No packaged install spec is present; the SKILL.md includes shell commands to create a Python venv and pip install faster-whisper. Using pip in an isolated venv is a reasonable install mechanism. The packages pulled (faster-whisper and its deps) come from PyPI/huggingface and are expected for transcription. There is no download from untrusted personal URLs or extract-from-URL steps in the manifest.
Credentials
The skill declares no environment variables or credentials, which is proportional. However, faster-whisper/huggingface-hub will perform network downloads of model artifacts (potentially large) and could prompt for HF auth if private models are used; the SKILL.md does not explicitly call this out. No unrelated secrets or config paths are requested.
Persistence & Privilege
The skill is instruction-only and not always-enabled; it does not request elevated privileges or modify other skills. It proposes editing the agent's openclaw.json configuration (its own runtime configuration), which is appropriate for enabling STT/TTS.
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 voice-stt-tts - 安装完成后，直接呼叫该 Skill 的名称或使用
/voice-stt-tts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
v1.0.3
No significant changes detected in this version.
- No file changes were detected between versions.
- All installation and configuration instructions remain the same.
- Functionality and behavior are unchanged.
v1.0.2
- Changed default installation and script paths from `local-voice` to `voice-messages`
- Updated default language in transcription from Russian (`ru`) to English (`en`)
- Changed default TTS voice from `ru-RU-SvetlanaNeural` (Russian) to `en-US-JennyNeural` (English)
- Updated OpenClaw configuration examples to reflect new paths and English defaults
v1.0.1
No user-facing changes in this release.
- Version bump to 1.0.1 with no content or configuration updates.
- No modifications detected in files or documentation.
v1.0.0
- Initial release of the voice-stt-tts skill for OpenClaw.
- Provides full voice message support: speech-to-text (STT) using faster-whisper, and text-to-speech (TTS) replies using Edge TTS.
- Includes scripts and configuration guides for setting up local transcription in a Python virtual environment.
- Offers ready-to-use OpenClaw JSON configuration snippets for both STT and TTS.
- Designed for easy installation and immediate voice-to-voice functionality on supported platforms.
元数据
常见问题
Voice messaging setup 是什么？
Full voice message setup (STT + TTS) for OpenClaw using faster-whisper and Edge TTS. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 498 次。
如何安装 Voice messaging setup？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install voice-stt-tts」即可一键安装，无需额外配置。
Voice messaging setup 是免费的吗？
是的，Voice messaging setup 完全免费（开源免费），可自由下载、安装和使用。
Voice messaging setup 支持哪些平台？
Voice messaging setup 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 Voice messaging setup？
由 Dmitry Aksenkin（@aksenkin）开发并维护，当前版本 v1.0.3。
推荐 Skills