← Back to Skills Marketplace
22375
Downloads
33
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install edge-tts
Description
Text-to-speech conversion using node-edge-tts npm package for generating audio from text.
Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation.
Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Usage Guidance
Install this only if you are comfortable sending text you convert to Microsoft's online TTS service. Do not use it for secrets, regulated data, private documents, or confidential prompts, and periodically clean generated audio files from the temp directory if they may contain sensitive content.
Capability Analysis
Type: OpenClaw Skill
Name: edge-tts
Version: 2.0.0
The OpenClaw Edge-TTS skill is designed for text-to-speech conversion using the `node-edge-tts` npm package. All analyzed files, including `SKILL.md`, `install.sh`, `tts-converter.js`, and `config-manager.js`, demonstrate behavior strictly aligned with this stated purpose. File system operations are limited to creating temporary audio files in the system's temp directory and managing a user-specific configuration file (`~/.tts-config.json`). Network access is solely for connecting to the legitimate Microsoft Edge TTS service. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the agent to perform unauthorized actions. The skill's capabilities are appropriate for its function.
Capability Assessment
Purpose & Capability
The documented purpose, bundled scripts, dependencies, and runtime behavior all align around text-to-speech generation, voice options, subtitles, and configuration management.
Instruction Scope
The skill uses the generic keyword "tts" as an activation cue, which could cause accidental invocation if an agent treats casual mentions as commands, but this is a routing-scope issue rather than hidden or unrelated behavior.
Install Mechanism
Installation runs npm install in the scripts directory for node-edge-tts and commander; this is expected for the Node.js implementation, though npm dependency installation remains a normal supply-chain surface.
Credentials
Text submitted for conversion is sent to Microsoft's online TTS service and generated audio/subtitle files are written locally; this is proportionate for an online TTS skill and is disclosed, but users should avoid sensitive text.
Persistence & Privilege
The skill can persist user TTS preferences in ~/.tts-config.json and leaves generated audio in a temp directory unless cleaned up; no credential access, privilege escalation, background worker, or destructive persistence was found.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install edge-tts - After installation, invoke the skill by name or use
/edge-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
**Major upgrade with added scripts, configurability, and streamlined TTS triggers**
- Added Node.js scripts for TTS conversion and config management (`tts-converter.js`, `config-manager.js`), with installation and usage instructions.
- Added resource and reference files, including a complete voice/option guide and install script.
- Changed TTS intent detection to trigger only on the "tts" keyword (removes long trigger phrase lists), and clarified keyword filtering prior to conversion.
- Expanded documentation with workflow, usage examples, advanced configuration, troubleshooting, and testing instructions.
- Clarified default voice, output formats, temporary file handling, and recommended voice test site.
v1.0.0
- Initial release of edge-tts skill for high-quality text-to-speech conversion using the node-edge-tts npm package.
- Supports multiple voices, languages, speed, pitch, and subtitle generation.
- Provides built-in TTS tool and advanced Node.js scripts for customization.
- Detects a wide range of trigger phrases and keywords for automatic TTS activation.
- Includes configuration manager for persistent user preferences and extensive voice options.
- Default voice set to "en-US-MichelleNeural" with neural voice support for natural audio.
Metadata
Frequently Asked Questions
What is Edge TTS?
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output. It is an AI Agent Skill for Claude Code / OpenClaw, with 22375 downloads so far.
How do I install Edge TTS?
Run "/install edge-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Edge TTS free?
Yes, Edge TTS is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Edge TTS support?
Edge TTS is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Edge TTS?
It is built and maintained by i3130002 (@i3130002); the current version is v2.0.0.
More Skills