← 返回 Skills 市场
1251
总下载
0
收藏
3
当前安装
3
版本数
在 OpenClaw 中安装
/install mlx-tts
功能描述
Text-To-Speech with MLX (Apple Silicon) and opensource models (default QWen3-TTS) locally.
使用说明 (SKILL.md)
MLX TTS
Text-To-Speech with MLX (Apple Silicon) and open-source models (default QWen3-TTS) locally.
Free and Fast. No API key required. No server required.
Requirements
mlx: macOS with Apple Siliconbrew: used to install deps if not available
Installation
bash ${baseDir}/install.sh
This script will use brew to install these CLI tools if not available:
uv: install python package and run python scriptmlx_audio: do the real job
Usage
To generate audio from text, run this script:
bash ${baseDir}/mlx-tts.sh "\x3Ctext>"
Agent Instructions
- Run the script: Pass the text to be spoken as an argument.
- Handle Output: The script will output a path to a audio file.
Use the
messagetool to send the audio file to the user as an voice message:
{
"action": "send",
"filePath": "\x3Cfilepath>"
}
Example: User: "Say hello world" Agent:
- Runs
bash path/to/mlx-tts.sh "hello world" - Receives output:
/tmp/folder/audio.ogg - Calls
message(action="send", filePath="/tmp/folder/audio.ogg", ...)
安全使用建议
This skill likely does what it says (generates local TTS) but it will download and install a third‑party tool ('mlx-audio') as a pre-release package and downloads models at runtime. Key things to consider before installing: 1) always:true is set unnecessarily — disable or remove that unless you understand why it must be always-present; 2) inspect the sources for the 'uv' tool and the 'mlx-audio' package (where does 'uv' fetch from?), and prefer signed/official releases rather than forced pre-release installs; 3) run the install in a sandbox/VM or an isolated macOS user account and review what gets written to disk; 4) be prepared for large network and disk usage when models are downloaded; 5) if you cannot verify the upstream repositories or the package provenance, avoid enabling the skill on machines with sensitive data. If you want to proceed safely, run install.sh manually, audit installed files, and avoid granting broader privileges.
功能分析
Type: OpenClaw Skill
Name: mlx-tts
Version: 0.0.3
The skill bundle is designed for local Text-To-Speech functionality using MLX on Apple Silicon. The `install.sh` script uses `brew` and `uv` to install necessary dependencies (`ffmpeg`, `uv`, `mlx-audio`), which is standard for setting up a local environment. The `mlx-tts.sh` script processes user text, generates audio using `mlx_audio.tts.generate`, converts it with `ffmpeg`, and outputs the file path. The `SKILL.md` provides clear instructions for the agent to execute these scripts and handle the audio output. There is no evidence of data exfiltration, malicious execution (beyond installing legitimate tools for the stated purpose), persistence mechanisms, prompt injection attempts against the agent, or obfuscation.
能力评估
Purpose & Capability
The name/description (local TTS on Apple Silicon) aligns with the included scripts which call a local 'mlx_audio' tool and ffmpeg. Requiring brew is reasonable. However, the skill installs an external tool ('mlx-audio') and pulls models by name at runtime — this is consistent with the purpose but worth noting because it requires downloading third-party code and potentially large model weights.
Instruction Scope
Runtime instructions are narrowly scoped: run install.sh and mlx-tts.sh which produce a local audio file and return its path. The scripts do not read unrelated system files or request credentials. They do, however, execute commands that fetch and run external code and download models (the model string is passed to the tool), which is within the TTS goal but expands the attack surface.
Install Mechanism
No formal install spec in registry; install.sh uses brew and then runs 'uv tool install --force "mlx-audio" --prerelease=allow'. That command force-installs a pre-release third-party tool from the network without provenance. Installing remote/unverified code and pre-release packages increases risk — the install will write code to disk and enable execution of code not present in the registry.
Credentials
The skill does not request environment variables, credentials, or config paths. It only requires brew (and will install uv and ffmpeg). There are no obvious requests for unrelated secrets or system configuration.
Persistence & Privilege
The skill is marked always:true, meaning it will be force-included in every agent run. There is no clear justification for always:true for a user-invoked TTS utility. Combined with the installer behavior (downloading and installing a third-party tool), this increases the blast radius if the tool or package supply chain is malicious or compromised.
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 mlx-tts - 安装完成后，直接呼叫该 Skill 的名称或使用
/mlx-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
v0.0.3
Version 0.0.3
- Added more usage triggers (e.g. "Say <text>", "Reply with voice message ...") for broader activation.
- Expanded documentation with agent instructions for handling and sending the generated audio files as voice messages.
- Updated wording and formatting in documentation for clarity and consistency.
- Removed the version field from SKILL.md metadata for simplified versioning.
v0.0.2
- Updated SKILL.md to reflect new usage instructions and correct script name.
- Added note about initial model download possibly causing slower first run.
- Updated metadata homepage link.
- Bumped version to 0.0.2.
v0.0.1
- Initial release of mlx-tts: local text-to-speech using MLX on Apple Silicon.
- Utilizes open-source models (default: QWen3-TTS).
- No API key or external server required.
- Supports automatic installation of required CLI tools via Homebrew.
- Provides simple CLI triggers for converting text to audio.
元数据
常见问题
MLX TTS 是什么？
Text-To-Speech with MLX (Apple Silicon) and opensource models (default QWen3-TTS) locally. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1251 次。
如何安装 MLX TTS？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mlx-tts」即可一键安装，无需额外配置。
MLX TTS 是免费的吗？
是的，MLX TTS 完全免费（开源免费），可自由下载、安装和使用。
MLX TTS 支持哪些平台？
MLX TTS 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin）。
谁开发了 MLX TTS？
由 guoqiao（@guoqiao）开发并维护，当前版本 v0.0.3。
推荐 Skills