Pywayne TTS for Openclaw

A versatile text-to-speech engine that converts text into high-quality Opus or MP3 audio files using local or cloud-based services.

wangyendt
v0.1.0
Feb 17, 2026
0
1.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install tts-2

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install tts-2 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 Pywayne TTS?

Pywayne TTS is a dedicated audio generation utility designed to enhance the capabilities of AI agents. By integrating this tool into your Openclaw Skills workflow, you gain the ability to synthesize speech from text using two distinct engines: the native macOS say command for rapid local processing and the Google TTS (gTTS) service for broader language support and cloud-based flexibility.

The skill focuses on efficiency and output quality, leveraging the power of ffmpeg to ensure that resulting audio files are optimized for their intended use. Whether you need the compact, high-fidelity benefits of the Opus format for voice applications or the universal compatibility of MP3 for multimedia playback, this tool provides a reliable bridge between text data and audible content.

Pywayne TTS Use Cases

  • Creating automated voice notifications for developer tools and AI agents.
  • Generating localized audio clips for training materials or presentations.
  • Converting long-form text into portable MP3 files for offline listening.
  • Integrating high-quality voice output into custom Openclaw Skills or automation scripts.

How Pywayne TTS Works

  1. The user provides a text string and specifies a target filename with either an .opus or .mp3 extension.
  2. The skill identifies the host platform and checks for the presence of the ffmpeg dependency.
  3. Based on the configuration, it chooses between the macOS native synthesis engine or the Google TTS API.
  4. The raw audio stream is captured and processed through ffmpeg to meet specific codec requirements (e.g., 16kHz mono for Opus).
  5. The final audio file is written to the disk, and all intermediate temporary files are automatically scrubbed from the system.

Pywayne TTS Setup

To utilize Pywayne TTS within your Openclaw Skills environment, ensure ffmpeg is installed on your system.

# For macOS users
brew install ffmpeg

# For Ubuntu/Debian users
sudo apt update && sudo apt install ffmpeg

# Install the required Python library
pip install gtts

Pywayne TTS Data Schema & Taxonomy

The skill manages audio production through structured parameters and automated file handling. Below is the schema for the audio output specifications:

Feature Opus Format MP3 Format
Sample Rate 16kHz Variable (Standard)
Channels Mono Stereo/Mono
Use Case Voice calls / Small size General playback
Engine macOS say / gTTS macOS say / gTTS

All files are generated based on the opus_filename or mp3_filename provided in the function call.

Pywayne TTS Advanced Features

  • Smart platform detection that prioritizes native macOS resources for lower latency.
  • Manual engine override via the use_say parameter to force Google TTS on macOS systems.
  • Automated ffmpeg integration for precise audio encoding and normalization.
  • Robust cleanup routines that prevent local storage bloat by removing temporary files immediately after conversion.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*