A comprehensive speech interaction skill providing high-fidelity Text-to-Speech and Automatic Speech Recognition with intelligent engine switching.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install kid-point-voice-component
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 kid-point-voice-component 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 SenseAudio Voice?
SenseAudio Voice is a robust audio processing skill designed for Openclaw agents, combining the power of the SenseAudio HTTP API with Microsoft Edge TTS. It provides a complete voice interaction loop, supporting both speech synthesis (TTS) and recognition (ASR). The skill is engineered for versatility, automatically selecting the most appropriate engine based on the input language—utilizing SenseAudio for high-quality Chinese synthesis and Edge TTS for seamless English and Japanese output.
Built for reliability and ease of use, this skill requires minimal dependencies beyond the standard Python requests library. It generates system-compatible WAV and MP3 files, ensuring broad compatibility across different operating systems. Whether you are building an educational assistant for kids or a multilingual productivity tool, SenseAudio Voice offers a professional-grade audio foundation within the Openclaw Skills ecosystem.
SenseAudio Voice Use Cases
- Creating interactive voice-based educational agents for language learning.
- Building hands-free productivity tools that read out tasks or notifications.
- Developing multilingual AI assistants that switch naturally between Chinese, English, and Japanese.
- Archiving voice interactions by generating timestamped audio logs in organized directories.
- Testing audio playback and hardware compatibility for AI-driven hardware projects.
How SenseAudio Voice Works
- The user provides a text string via the CLI or agent interface.
- The skill performs automatic language detection to identify if the content is Chinese, Japanese, or Latin-based text.
- Based on the detected language and configuration, it selects either the SenseAudio engine or Microsoft Edge TTS engine.
- The selected engine processes the request and returns an audio stream or file.
- The skill saves the resulting audio to a timestamped workspace directory (e.g.,
audio/YYYY-MM-DD/). - If the playback flag is enabled, the skill automatically detects available system players (like ALSA or PulseAudio) and plays the audio immediately.
SenseAudio Voice Setup
To integrate this skill into your environment, follow these steps:
- Ensure you have the requests library installed:
pip install requests
- Configure your SenseAudio API Key in your Openclaw configuration file located at
~/.openclaw/openclaw.json:
{
"env": {
"SENSE_API_KEY": "your_api_key_here"
}
}
- Verify your system audio players:
python scripts/tts.py --check-players
SenseAudio Voice Data Schema & Taxonomy
SenseAudio Voice organizes generated assets within the agent's workspace using a clear chronological taxonomy:
| Path Component | Description |
|---|---|
{workspace}/audio/ |
The root directory for all audio assets. |
YYYY-MM-DD/ |
Sub-directories organized by date. |
HHMMSS_voice_text.mp3 |
Filename format including time, voice ID, and text prefix. |
Users can override the default storage behavior using the -o or --output flag to specify custom file paths.
SenseAudio Voice Advanced Features
- Intelligent engine fallback: Automatically degrades to Edge TTS if SenseAudio is unavailable for non-Chinese text.
- Multi-voice support: Access specific voice IDs like child_0001_a for friendly interactions or en-US-GuyNeural for professional English output.
- Granular audio control: Adjust speech speed (0.5 to 2.0) and volume (0 to 10) dynamically.
- Automated ASR: High-precision speech-to-text recognition via the SenseAudio ASR endpoint.
- Format flexibility: Choose between WAV for raw compatibility or MP3 for storage efficiency via the --format flag.
SKILL.md
Loading
Related Openclaw Skills
Chart Master
A Python-powered financial charting engine for generating professional candlestick, OHLC, and technical analysis visualizations.
Roadmap
A professional command-line tool for planning product roadmaps, tracking milestones, and visualizing development progress.
GitHub Radar
GitHub Radar is an advanced open-source intelligence engine designed for AI Product Managers to extract high-level paradigm insights and ecosystem trends from GitHub data.
Install Chinese Fonts
A specialized automation skill to install and verify CJK fonts on Linux systems to resolve rendering issues in web and document environments.
IMAP/SMTP Email Tool
A comprehensive automation tool for reading, searching, and sending emails via standard protocols across multiple providers using Openclaw Skills.
Strategy Consultant Skill
A professional-grade strategy consultancy toolkit for AI agents featuring real-time market intelligence, expert network access, and automated business documentation.
Featured*
