← 返回 Skills 市场
7120
总下载
1
收藏
38
当前安装
1
版本数
在 OpenClaw 中安装
/install kokoro-tts
功能描述
Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to "say" something, requests a voice message, or wants text converted to speech.
安全使用建议
Install this if you trust the Kokoro endpoint you will use. Prefer the localhost default, avoid sending secrets or sensitive private text to an untrusted remote server, and expect generated audio files to accumulate in the local media directory.
功能分析
Type: OpenClaw Skill
Name: kokoro-tts
Version: 0.1.0
The skill is designed to generate speech using a configurable Kokoro TTS API. It makes a network POST request to the API_URL (defaulting to localhost) with user-provided text, voice, and speed, then saves the resulting audio to a local 'media' directory. There is no evidence of prompt injection in SKILL.md, malicious execution (user input is JSON-encoded, not executed), data exfiltration beyond sending the requested text to the configured TTS endpoint, or persistence mechanisms. All file and network operations are directly aligned with the stated purpose of a text-to-speech skill.
能力评估
Purpose & Capability
The stated purpose, instructions, and script behavior align: it takes text, optional voice and speed settings, posts them to a Kokoro TTS endpoint, and writes a generated MP3.
Instruction Scope
The trigger wording includes broad requests to "say" something, which could be ambiguous in an agent, but the documented action is still limited to user-requested speech generation and contains no hidden control instructions.
Install Mechanism
The skill has no installer or package mutation behavior, but it assumes Node.js and uses an optional KOKORO_API_URL environment variable that are documented in SKILL.md rather than explicit install metadata.
Credentials
Network transfer of the input text is necessary for TTS and defaults to localhost; if the user configures a remote endpoint, the spoken text will be sent to that server.
Persistence & Privilege
The script creates a local media directory and writes timestamped MP3 outputs only; it does not request credentials, read local profiles, install persistence, or perform destructive actions.
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 kokoro-tts - 安装完成后，直接呼叫该 Skill 的名称或使用
/kokoro-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
v0.1.0
kokoro-tts 0.1.0
- Initial release of the Kokoro TTS skill for generating speech audio from text.
- Supports configuration via the KOKORO_API_URL environment variable.
- Includes a Node.js script for generating audio files with customizable voice and speed.
- Outputs MP3 file paths in a format compatible with OpenClaw for automatic audio attachment.
- Provides several built-in voice options and instructions for listing all available voices.
元数据
常见问题
Kokoro TTS 是什么？
Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to "say" something, requests a voice message, or wants text converted to speech. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 7120 次。
如何安装 Kokoro TTS？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kokoro-tts」即可一键安装，无需额外配置。
Kokoro TTS 是免费的吗？
是的，Kokoro TTS 完全免费（开源免费），可自由下载、安装和使用。
Kokoro TTS 支持哪些平台？
Kokoro TTS 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 Kokoro TTS？
由 edkief（@edkief）开发并维护，当前版本 v0.1.0。
推荐 Skills