A high-performance, GPU-free text-to-speech skill for Windows that leverages built-in SAPI5 and Neural voices for instant audio generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sapi-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 sapi-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 SAPI5 TTS (Windows)?
The SAPI5 TTS skill is a lightweight alternative to resource-heavy AI voice models, designed specifically for Windows 10 and 11 environments. By utilizing the native Windows Speech API (SAPI5), this Openclaw Skills entry provides near-instant audio generation without requiring a GPU or complex local model hosting. It is optimized to automatically detect the best available voices on your system, ensuring high-quality output for developers and agents operating in local environments.
This skill bridges the gap between AI processing and human-like interaction by providing a reliable, low-latency speech synthesis layer. Whether you are using legacy desktop voices or modern Windows 11 Neural voices, this tool ensures your agent can communicate audibly without taxing system resources, making it a perfect addition to any Openclaw Skills collection.
SAPI5 TTS (Windows) Use Cases
- Providing real-time voice feedback for AI agent interactions and task completions.
- Generating high-quality audio notifications for long-running CLI automation workflows.
- Building accessible interfaces for Windows-based applications and tools.
- Creating multi-lingual audio assets locally without incurring cloud API costs or latency.
How SAPI5 TTS (Windows) Works
- The skill initializes the System.Speech.Synthesis.SpeechSynthesizer assembly via a PowerShell script.
- It scans the Windows registry for installed SAPI5 voices, prioritizing Neural or Online variants for superior quality.
- User-provided text is passed to the engine with optional parameters for language, rate, and specific voice selection.
- The synthesizer generates a WAV file and saves it to a structured local directory.
- If the play flag is active, the skill utilizes the .NET MediaPlayer to output the audio through the system's default device immediately.
SAPI5 TTS (Windows) Setup
To integrate this into your Openclaw Skills library, save the provided script as tts.ps1 in your designated skills directory. Ensure you have Windows SAPI5 voices installed (default on Win 10/11).
Verify your installation and list available voices using:
.\tts.ps1 -ListVoices
Generate your first audio file with:
.\tts.ps1 "Hello, this is a test of Openclaw Skills." -Play
SAPI5 TTS (Windows) Data Schema & Taxonomy
The skill manages its output within a dedicated workspace to ensure data persistence and organization.
| Attribute | Specification |
|---|---|
| Workspace Path | $env:USERPROFILE\.openclaw\workspace\tts\ |
| File Format | WAV (standard PCM) |
| Naming Convention | sapi_YYYYMMDD_HHmmss.wav |
| Metadata Logging | CLI output provides the selected voice name, culture, and absolute file path. |
SAPI5 TTS (Windows) Advanced Features
- Automatic best-voice selection based on language mapping (FR, EN, DE, ES, IT).
- Full support for NaturalVoiceSAPIAdapter to enable high-fidelity web-based neural voices.
- Configurable speech rate parameters ranging from -10 (slowest) to +10 (fastest).
- Partial name matching for voice selection, allowing users to target specific personas easily.
- Headless generation mode for background audio processing and media asset creation.
SKILL.md
Loading
Related Openclaw Skills
External KI Integration
A versatile skill that enables AI agents to access external intelligence through browser automation and API endpoints like ChatGPT, Claude, and Hugging Face.
External AI Integration
Integrate external LLMs like ChatGPT and Claude directly into your agent's workflow as callable tools using browser automation or APIs.
Error Recovery Automation
A robust framework for automating the detection and self-healing of common system failures in AI agent environments.
Cart Management
A technical blueprint for implementing robust React shopping cart state management with duplicate prevention and persistent storage.
Home Assistant Controller
Manage and automate your Home Assistant smart home devices directly through your AI agent.
SkillForge
SkillForge transforms YouTube videos into structured, reusable skill files to expand the knowledge base of any AI agent.
Featured*
