A high-performance, local Vietnamese text-to-speech engine with zero-shot voice cloning capabilities.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install valtec-tts
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install valtec-tts using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Valtec Vietnamese TTS is a powerful local speech synthesis tool powered by the VITS2 architecture, designed specifically for high-quality Vietnamese audio generation. Unlike cloud-based solutions, this skill operates entirely offline, ensuring data privacy and reducing latency for voice-enabled applications. It provides a robust set of Openclaw Skills for developers looking to integrate natural-sounding Vietnamese voices into their workflows without relying on external APIs.
The skill excels in providing diverse vocal options, including Northern and Southern dialects for both male and female speakers. Its standout feature is the zero-shot voice cloning, which allows users to replicate a specific voice using only a five-second reference audio clip. This makes it an essential addition to the library of Openclaw Skills for creating personalized AI interactions or localized content.
First, clone the repository and install the necessary Python dependencies to prepare your environment for Openclaw Skills usage:
git clone https://github.com/tronghieuit/valtec-tts.git ~/.openclaw/tools/valtec-tts
cd ~/.openclaw/tools/valtec-tts
pip install -e .
Then, update your ~/.openclaw/openclaw.json configuration to include the environment variable for this specific skill:
{
"skills": {
"entries": {
"valtec-tts": {
"env": {
"VALTEC_TTS_DIR": "~/.openclaw/tools/valtec-tts"
}
}
}
}
}
The skill utilizes a CLI-based schema for managing audio synthesis. On the first run, it downloads approximately 300MB of model weights to the local cache. The following parameters define how the skill organizes its output:
| Flag | Default | Description |
|---|---|---|
--speaker |
NF |
Pre-defined voice: NF (North Female), SF (South Female), NM1/2 (North Male), SM (South Male) |
--zeroshot |
N/A | Enables cloning from reference audio |
--reference |
N/A | Path to 3-10 second source WAV file |
-o, --output |
tts.wav |
Destination path for the generated audio file |
--speed |
1.0 |
Playback speed adjustment (range 0.5 to 2.0) |
Loading
An automated tool to generate professional LaTeX-based math worksheets, step-by-step answer keys, and study guides for K-12 education.

A high-performance local voice processing engine for Apple Silicon that provides sub-second TTS and STT capabilities without cloud dependency.

A specialized skill for AI agents to solve challenges and mint Base Buds NFTs on the Base mainnet using secure local signing.

A privacy-respecting metasearch skill that aggregates results from Google, Bing, and DuckDuckGo via a self-hosted SearXNG instance.

A specialized automation skill that appends text bullet points directly into your FocusNote daily logs via the local filesystem.

A comprehensive integration tool for managing members, invoices, and events through the easyVerein v2.0 REST API.








































