skills.rest
marcoamu
marcoamuCOMMUNITY
Explore all skills by this author →
GitHub

kokoro-tts

Convert input text to MP3 speech using the Kokoro TTS API.

1|Updated Mar 14, 2026
Search Tags:#voice#text-to-speech#audio#tts#speech#kokoro
One-click install
npx skills add https://github.com/marcoamu/openclaw-workspace --skill kokoro-tts-marcoamu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kokoro-tts
Source: https://github.com/marcoamu/openclaw-workspace/tree/main/skills/kokoro-tts
Command: npx skills add https://github.com/marcoamu/openclaw-workspace --skill kokoro-tts-marcoamu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill enables you to generate spoken audio from text using a Kokoro TTS service, allowing voices to be produced locally or remotely.

Core Features & Use Cases

  • Generate speech from text using a Kokoro TTS API, with configurable voice and speed.
  • Output MP3 audio files that can be attached to messages or stored in media.
  • Use Case: Convert a message into a spoken clip for an audio note or accessibility.

Quick Start

Run the tts.js script with your text to generate a spoken audio file.

Frequently Asked Questions about kokoro-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech locally using a custom TTS service?▼

To convert text to speech locally, this Skill sends input text to a Kokoro TTS API endpoint. You need to set the KOKORO_API_URL environment variable, provide a text string, and the script outputs an MP3 audio file.

Can I generate voice messages for chat assistants from text input?▼

Yes, you can generate voice messages for chat assistants from text input. The Skill processes the text via the Kokoro TTS API and outputs an MP3 file, which can be attached to chat responses for accessibility or voice notes.

Do I need an environment variable to use the Kokoro TTS API for audio generation?▼

Yes, you need the KOKORO_API_URL environment variable to use the Kokoro TTS API for audio generation. This variable points the script to your local or remote TTS service endpoint to process the text and return the MP3 output.

What is the best way to customize the voice and speed for text-to-speech conversion?▼

The best way to customize voice and speed for text-to-speech conversion is by passing optional voice and speed parameters to the TTS script. Along with your required text input, these parameters configure how the Kokoro API generates the spoken MP3 audio.

What audio format does the Kokoro TTS script output for spoken text?▼

The Kokoro TTS script outputs MP3 audio files for spoken text. After you provide the text input and optional voice configurations, the generated speech is saved as an MP3 file that can be stored or attached to messages.

Are there limitations when using a local text-to-speech API for generating audio clips?▼

A limitation when using this local text-to-speech API is that it depends entirely on the availability of your configured KOKORO_API_URL endpoint. It requires a separate running Kokoro service instance to process requests and output the MP3 speech files.

Related Skills

Explore More Content & Communication Skills→
papdawinpapdawin

tts-service

Serve Hungarian text-to-speech via FastAPI endpoints with per-tenant voice configuration.

Community
Intermediate
ViewWayViewWay

tts

Generate MP3 speech from text using Hume AI or OpenAI.

Community
Advanced
yazelinyazelin
31

voice

Convert voice messages to text and generate spoken responses.

Community
Intermediate
rahulrajaramrahulrajaram

speak

Convert input text to spoken audio using the Kokoro TTS engine.

Community
Basic