A powerful text-to-speech synthesis tool leveraging Tencent Cloud's API to generate high-fidelity audio files from any text input.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tencentcloud-tts
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 tencentcloud-tts 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 Tencent TTS?
The Tencent TTS skill is a technical integration designed to bring professional-grade speech synthesis to the Openclaw Skills ecosystem. By connecting directly to Tencent Cloud's Text-to-Speech engine, this skill allows AI agents to produce natural-sounding voice outputs in various formats such as MP3 and WAV. It is built for developers who need reliable, scalable, and customizable audio generation for their automated workflows.
This skill focuses on simplicity and security, using environment variables for credential management to ensure your API keys remain protected. Whether you are building an interactive AI assistant or a content automation pipeline, this addition to your Openclaw Skills library provides the essential tools to bridge the gap between text and audio.
Tencent TTS Use Cases
- Automating the creation of audiobooks or narrated articles from written content.
- Developing voice-enabled user interfaces for AI agents within the Openclaw Skills framework.
- Generating localized voice prompts for applications and IoT devices.
- Building accessibility tools that convert real-time text data into audible speech for better user engagement.
How Tencent TTS Works
- The user provides a text string and optional parameters like voice type or file format to the skill.
- The skill retrieves the Tencent Cloud SecretId and SecretKey from the local environment variables for secure authentication.
- A request is sent to the Tencent Cloud TTS API to process the provided text using the specified voice model.
- The API returns the synthesized audio data, which the skill then saves as a local file (e.g., output.mp3).
- The skill provides the path of the generated audio file back to the Openclaw Skills agent for immediate use or further distribution.
Tencent TTS Setup
To get started, you must have an active Tencent Cloud account with the TTS service enabled. Obtain your API credentials from the Tencent Cloud Console and configure them in your environment:
export TENCENTCLOUD_SECRET_ID="your-secret-id"
export TENCENTCLOUD_SECRET_KEY="your-secret-key"
Ensure your development environment is configured to run Python scripts as defined in the Openclaw Skills structure. You can then initialize the TextToSpeech class and call the synthesize method to generate audio.
Tencent TTS Data Schema & Taxonomy
The Tencent TTS skill organizes its operations through a structured set of parameters and generated outputs. The following table describes the data configuration:
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| text | string | Yes | - | The input text to be synthesized into speech. |
| voice_type | int | No | 101001 | The ID of the voice model (ranging from 101001 to 101015). |
| codec | string | No | mp3 | The audio encoding format, supporting mp3 or wav. |
| output_file | string | No | output.mp3 | The filename for the generated audio file. |
All generated files are saved within the project's local directory for easy access by other Openclaw Skills components.
Tencent TTS Advanced Features
- Support for multiple high-fidelity audio codecs (MP3/WAV) to suit different project requirements.
- Configurable voice models allowing users to select between various genders and speaking styles.
- Secure integration with Tencent Cloud's API via environment-based secret management.
- Lightweight Python implementation that can be easily extended or integrated into complex Openclaw Skills multi-agent workflows.
- Best-practice recommendations included for handling rate limits and managing long-form text synthesis.
SKILL.md
Loading
Related Openclaw Skills
WeChat Search
A multi-layered search tool for retrieving WeChat Official Account articles through compliant APIs and intelligent fallbacks.
WeChat Search Skill
A specialized search utility for discovering and extracting metadata from WeChat Official Account articles using a compliant, multi-layered approach.
Aliyun OSS File Upload
A secure and efficient tool for managing Aliyun Object Storage Service (OSS) uploads and generating temporary access links.
Aliyun Mail
A professional-grade skill for automating enterprise email communication through Aliyun with full support for Markdown, attachments, and syntax highlighting.
Gold Price MCP Skill
A specialized MCP skill for AI agents to retrieve live Thai gold prices from official central APIs.
Pepsi or Coke Decision Agent
A specialized decision-making utility that allows AI agents to programmatically choose between two leading beverage brands.
Featured*
