← Back to Skills Marketplace
7856
Downloads
2
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install kokoro-tts
Description
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.
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
Purpose & Capability
The stated purpose, documentation, and script behavior are coherent: text, voice, and speed are posted to a Kokoro speech API and the returned audio is written as an MP3.
Instruction Scope
The trigger phrase asking to "say" something is broad and could be invoked ambiguously, but the documented action remains limited to user-requested speech generation.
Install Mechanism
There is no installer or dependency mutation behavior; the skill relies on Node.js and documents the optional KOKORO_API_URL environment configuration.
Credentials
Network transfer of the input text is proportionate for API-backed TTS and defaults to localhost, but configuring a remote endpoint means the spoken text is sent to that server.
Persistence & Privilege
The script only creates a local media directory and timestamped MP3 output files; it does not read credentials, install persistence, spawn background workers, or perform destructive actions.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install kokoro-tts - After installation, invoke the skill by name or use
/kokoro-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Frequently Asked Questions
What is Kokoro TTS?
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. It is an AI Agent Skill for Claude Code / OpenClaw, with 7856 downloads so far.
How do I install Kokoro TTS?
Run "/install kokoro-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Kokoro TTS free?
Yes, Kokoro TTS is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Kokoro TTS support?
Kokoro TTS is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Kokoro TTS?
It is built and maintained by edkief (@edkief); the current version is v0.1.0.
More Skills