← 返回 Skills 市场
166
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install voice-for-openclaw
功能描述
MiniMax TTS skill (enhanced). Multi-agent voice support (each agent can select a unique voice written in SOUL.md), native voice message for Telegram (MP3) an...
安全使用建议
This skill appears to do only TTS via MiniMax and optional channel delivery. Before installing: (1) keep MINIMAX_API_KEY and any TELEGRAM_BOT_TOKEN in the local .env (do not commit it); (2) review the scripts yourself (they are included) to confirm behavior; (3) note generated audio is written to ~/.openclaw/workspace/generated — delete files if they contain sensitive content; (4) if you will use Telegram sending, provide a bot token with only the required access and verify target chat IDs; (5) confirm the API endpoint (api.minimaxi.com) is acceptable for your data/privacy needs.
功能分析
Type: OpenClaw Skill
Name: voice-for-openclaw
Version: 1.0.2
The skill provides Text-to-Speech (TTS) functionality using the MiniMax API, with support for sending voice messages to Telegram and Feishu. The implementation consists of a Python script (tts.py) for API interaction and a shell script (tts-xiaoye.sh) for workflow orchestration and channel delivery. All network activities are directed to legitimate endpoints (api.minimaxi.com and api.telegram.org), and sensitive credentials like API keys are handled via environment variables or a local .env file as described in the documentation.
能力评估
Purpose & Capability
Name/description, required binaries (python3, ffmpeg), and required env (MINIMAX_API_KEY) match an API-driven TTS skill that can optionally send to Telegram. Optional TELEGRAM_* vars are explained as optional for message delivery.
Instruction Scope
Instructions and scripts only call the MiniMax TTS endpoint and (optionally) Telegram/Feishu delivery paths, read a local .env and write audio files under ~/.openclaw/workspace. They do export .env keys at runtime and show examples invoking 'openclaw message send' for Feishu; these are within the stated TTS/delivery scope but users should be aware audio files and credentials are read/stored locally.
Install Mechanism
No install spec or external downloads. The skill is instruction/code-only and relies on standard binaries (python3, ffmpeg) and Python requests — no arbitrary network installs or remote archives.
Credentials
Only the MiniMax API key is required; optional Telegram vars are clearly optional. No unrelated cloud credentials or broad-scoped secrets are requested.
Persistence & Privilege
always is false and the skill does not request elevated platform privileges or modify other skills. It writes audio files under the user's workspace (~/.openclaw/workspace) which is expected for generated content.
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-for-openclaw - 安装完成后，直接呼叫该 Skill 的名称或使用
/voice-for-openclaw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
v1.0.2
Fix tts.py and tts-xiaoye.sh skill path references
v1.0.1
Fix skill path references to match folder name
v1.0.0
Initial release: MiniMax TTS skill renamed to Voice-for-OpenClaw
元数据
常见问题
Voice For Openclaw Publish 是什么？
MiniMax TTS skill (enhanced). Multi-agent voice support (each agent can select a unique voice written in SOUL.md), native voice message for Telegram (MP3) an... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 166 次。
如何安装 Voice For Openclaw Publish？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install voice-for-openclaw」即可一键安装，无需额外配置。
Voice For Openclaw Publish 是免费的吗？
是的，Voice For Openclaw Publish 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Voice For Openclaw Publish 支持哪些平台？
Voice For Openclaw Publish 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 For Openclaw Publish？
由 vshen009（@vshen009）开发并维护，当前版本 v1.0.2。
推荐 Skills