A robust Text-to-Speech skill that converts text into high-quality audio files with support for over 90 voices and various emotional styles.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tts-wangwang
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tts-wangwang using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is TTS - Advanced Text-to-Speech for AI Agents?
The TTS skill is a sophisticated extension for AI agents within the Openclaw Skills ecosystem, designed to bridge the gap between text and audio. It enables developers and users to transform written content into natural-sounding speech files (MP3) effortlessly. By utilizing a free, high-performance API, this skill allows for the creation of voice-enabled responses, making AI interactions more accessible and engaging.
This skill is built for flexibility, allowing agents to choose from a wide variety of voice profiles and adjust parameters such as speed, pitch, and emotional tone. Whether you are building an automated narrator, a voice assistant, or a messaging bot, the inclusion of this functionality via Openclaw Skills ensures a seamless integration process without the need for complex API key management.
TTS - Advanced Text-to-Speech for AI Agents Use Cases
- Automating the creation of audiobooks or voiceovers for long-form text content.
- Providing accessibility features by reading out chat responses or documentation.
- Generating character-specific voices for interactive gaming or storytelling agents.
- Batch converting notifications and alerts into audio format for hands-free monitoring.
How TTS - Advanced Text-to-Speech for AI Agents Works
- The AI agent identifies a user request involving voice generation, such as 'read this out' or 'convert to audio'.
- The skill constructs a POST request containing the input text and desired voice parameters (ID, speed, pitch).
- The request is sent to the high-speed TTS endpoint which processes the synthesis in real-time.
- The resulting audio stream is captured and saved as a local MP3 file in the system's temporary directory.
- The agent utilizes a messaging tool to deliver the absolute file path or the media file itself back to the user.
TTS - Advanced Text-to-Speech for AI Agents Setup
To deploy this skill, ensure your environment can execute HTTP POST requests. No authentication tokens are required for the primary endpoint. You can verify the installation using the following command:
curl -s -X POST 'https://tts.wangwangit.com/v1/audio/speech' \
-H 'content-type: application/json' \
-d '{"input":"Hello from Openclaw Skills","voice":"zh-CN-YunyangNeural","speed":1.0,"style":"general"}' \
-o /tmp/test_voice.mp3
TTS - Advanced Text-to-Speech for AI Agents Data Schema & Taxonomy
The skill manages data through a structured JSON request body and outputs binary audio files. The following table describes the metadata schema for synthesis requests:
| Field | Type | Required | Description |
|---|---|---|---|
| input | string | Yes | The text to be converted (max 10,000 characters) |
| voice | string | Yes | The specific Voice ID (e.g., zh-CN-XiaoxiaoNeural) |
| speed | float | No | Playback rate ranging from 0.25 to 3.0 (default 1.0) |
| pitch | string | No | Tone adjustment from -50 to +50 (default 0) |
| style | string | No | Emotional context like assistant, chat, or cheerful |
Output files are typically generated as MP3 by default but support extensions like WAV, OGG, or AMR.
TTS - Advanced Text-to-Speech for AI Agents Advanced Features
- Support for over 90 unique voice identities across different genders and tones.
- Contextual style switching, allowing the agent to sound like a newscaster, a customer service representative, or a friendly assistant.
- High-volume text handling with a single-request limit of 10,000 characters for long-form synthesis.
- Seamless integration with Openclaw Skills message actions for direct media dispatch to end-user interfaces.
SKILL.md
Loading
Related Openclaw Skills
PRD to Issues
A high-efficiency decomposition tool that transforms Product Requirements Documents into independent, end-to-end GitHub issues.
Daily Decision Helper
A structured AI framework for evaluating daily decisions through pros-cons analysis and weighted factor modeling.
TQSDK Market Data Reader
A specialized tool for fetching real-time quotes, K-line sequences, and historical market data from the Chinese futures and options markets.
Senior Backend Developer
A production-grade backend engineering skill for implementing secure APIs, database architectures, and robust server-side logic.
Alibaba Cloud DevOps (Yunxiao) MCP Server
A powerful Model Context Protocol server that integrates the full suite of Alibaba Cloud Yunxiao DevOps tools into your AI agent environment.
js2java: JavaScript to Java Translation Assistant
A powerful tool for frontend developers to translate JavaScript business logic into enterprise-grade Java Spring Boot applications.
Featured*
