A sophisticated text-to-speech engine that intelligently handles mixed Vietnamese, Chinese, and English text with automatic Pinyin-to-Hanzi conversion.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install smart-speak-vutran
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 smart-speak-vutran 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 Smart-Speak Multilingual TTS?
Smart-Speak is a specialized addition to the ecosystem of Openclaw Skills designed to bridge the gap in multilingual audio generation. It solves the common issue where TTS engines struggle with mixed-language inputs, particularly when Pinyin is embedded within Vietnamese or English text. By leveraging intelligent segmentation and native-quality neural voices, it ensures that each language block is pronounced with the correct accent and tone.
The core strength of this skill lies in its pre-processing logic. It automatically detects Pinyin phonetic markers and converts them into Hanzi (Chinese characters) before synthesis. This step is crucial because it allows the Chinese TTS engine to interpret the semantic meaning and tonal requirements accurately, resulting in a seamless and natural listening experience for the end-user.
Smart-Speak Multilingual TTS Use Cases
- Creating language learning materials that require clear pronunciation of Vietnamese, Chinese, and English.
- Generating localized audio content for users who communicate using a mix of Pinyin and Vietnamese.
- Automating the production of high-quality multilingual voiceovers for technical documentation or messages.
- Developing interactive AI assistants that need to read out Chinese names or phrases accurately within a non-Chinese context.
How Smart-Speak Multilingual TTS Works
- The agent analyzes the input text to identify specific language segments and detect Pinyin based on phonetic patterns.
- Detected Pinyin is converted into Hanzi characters to optimize pronunciation accuracy for the Chinese TTS engine.
- Emojis are stripped to prevent unwanted verbal descriptions, and punctuation is normalized to ensure natural pauses.
- The text is divided into a JSON-based list of segments, each assigned a specific neural voice (e.g., Hoài Mỹ for Vietnamese, Xiaoxiao for Chinese).
- A Python backend executes the synthesis for each block and utilizes ffmpeg to merge them into a final MP3 file.
- The completed audio file is delivered to the user via the workspace file path.
Smart-Speak Multilingual TTS Setup
To integrate this into your environment for Openclaw Skills, ensure you have the necessary dependencies installed:
# Install the edge-tts engine
pip install edge-tts
# Ensure ffmpeg is available for audio merging
sudo apt update && sudo apt install ffmpeg
# The skill script is located at:
# skills/public/smart-speak/scripts/smart_speak.py
Note: The script expects the edge-tts binary to be located at ~/.local/bin/edge-tts.
Smart-Speak Multilingual TTS Data Schema & Taxonomy
Smart-Speak organizes data using a structured segment approach to ensure high-fidelity merging.
| Attribute | Description |
|---|---|
text |
The processed string (Hanzi/English/Vietnamese) to be spoken. |
voice |
The specific Neural voice ID assigned to the segment. |
output |
Absolute path to the generated .mp3 file in the workspace. |
All segments must be passed as a properly escaped JSON string via the --segments-json flag.
Smart-Speak Multilingual TTS Advanced Features
- Intelligent Pinyin-to-Hanzi Mapping: Goes beyond simple TTS by understanding the phonetic context of Chinese characters.
- Multi-Engine Merging: Seamlessly combines outputs from different neural voices into a single cohesive audio file.
- Neural Voice Selection: Utilizes premium voices like
vi-VN-HoaiMyNeuralandzh-CN-XiaoxiaoNeuralfor human-like prosody. - Workspace Integration: Built-in support for absolute path handling within Openclaw Skills environments.
SKILL.md
Loading
Related Openclaw Skills
Gemini Smart Search
A specialized search skill for Openclaw agents that leverages Gemini with Google Search grounding and intelligent model fallback routing.
TRON Account Profiling
A comprehensive analytical tool for profiling TRON addresses, covering assets, resources, staking, and on-chain behavior.
OpenBook
An open-source platform for recording and searching real-time, structured observations about physical businesses and locations.
Material Review
Material Review is a specialized AI agent skill designed to audit data sharing catalogs and ensure consistency between documentation and platform records.
Agent Content Analyzer
A professional tool for analyzing AI Agent news data to extract trending topics, evaluate market heat, and generate actionable content creation inspiration.
CapCut Mate Automation
A comprehensive automation skill for CapCut that enables AI agents to create, edit, and render video drafts via a local or cloud-based API.
Featured*
