A high-definition generative speech synthesis skill utilizing Google Cloud Chirp 3 HD models for ultra-realistic, emotionally expressive audio output.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install g-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 g-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 Google Chirp 3 HD TTS?
The Google Chirp 3 HD TTS skill is a premium audio generation tool designed for AI agents within the Openclaw Skills ecosystem. By leveraging Google's latest LLM-based generative audio models, it delivers a level of realism, emotional expressiveness, and natural pacing that traditional text-to-speech engines cannot match. This skill is specifically engineered to handle complex human-like prosody, making it ideal for applications requiring a high degree of empathy or conversational fluidity.
Built with portability in mind, this skill manages its own dependencies locally, ensuring that the environment remains clean while still providing access to the powerful @google-cloud/text-to-speech library. It transforms raw text into sophisticated audio files, allowing developers to create more immersive and interactive AI-driven experiences.
Google Chirp 3 HD TTS Use Cases
- Creating natural-sounding voice assistants that use conversational contractions and realistic fillers.
- Generating high-quality audio versions of long-form articles or reports with strategic pauses.
- Developing interactive storytelling or roleplay agents that require specific emotional tones provided by HD voices.
- Automating voice notifications in professional environments where human-like clarity is essential.
- Enhancing accessibility by providing readable content through high-fidelity generative speech.
How Google Chirp 3 HD TTS Works
- Intent Detection: The system identifies trigger keywords such as tts, speak, or voice within the user's request.
- Text Optimization: The agent applies prompt engineering to the input, adding contractions, ellipses, and specialized [pause] tags to ensure natural speech patterns.
- Environment Validation: The skill verifies that Node.js 18+ is present and checks for the existence of the OPENCLAW_WORKSPACE directory.
- Dependency Management: On first run, the skill automatically installs the necessary Google Cloud libraries locally within its folder using npm.
- Synthesis Execution: The core script is executed via Node.js, passing the formatted text, selected HD voice, and output path as arguments.
- Output Delivery: The skill returns an absolute file path to the generated MP3, confirming successful synthesis to the user.
Google Chirp 3 HD TTS Setup
To integrate this among your Openclaw Skills, ensure you have Node.js 18 or higher installed. You must also authenticate with Google Cloud using Application Default Credentials (ADC).
# Authenticate with Google Cloud
gcloud auth application-default login
# The skill handles internal dependencies automatically on the first run:
# npm install @google-cloud/text-to-speech --prefix "$SKILL_DIR"
Set the OPENCLAW_WORKSPACE environment variable to define where your audio files should be saved.
Google Chirp 3 HD TTS Data Schema & Taxonomy
The skill organizes its output and metadata as follows:
| Feature | Details |
|---|---|
| Output Format | High-quality MP3 audio files. |
| Storage Location | Defined by $OPENCLAW_WORKSPACE or defaults to the current working directory. |
| Tagging System | Uses [pause], [pause short], and [pause long] to map to SSML break tags. |
| Voice Taxonomy | Categorized by Gender (Female/Male) and HD Model name (e.g., Aoede, Charon). |
| Return Schema | Returns a string prefix SUCCESS: followed by the absolute system path. |
Google Chirp 3 HD TTS Advanced Features
- SSML Mapping: Automatically converts shorthand tags like
[pause]into complex SSML break durations for precise timing control. - Generative Prosody: Utilizes LLM-based generative models to interpret punctuation like ellipses and commas as natural breathing or hesitation points.
- Self-Healing Dependencies: Includes an auto-run logic that checks for and installs missing npm packages without user intervention.
- Flexible Voice Selection: Supports a wide array of specialized HD voices including Achernar, Puck, and Fenrir for diverse character profiles.
- Multi-Agent Integration: Designed to be called directly via CLI, allowing multiple AI agents to share the same generative speech capabilities.
SKILL.md
Loading
Related Openclaw Skills
Free Text to Video Long
A high-performance AI video generation tool that converts long-form text and scripts into professional 1080p MP4 videos without local hardware requirements.
7Sins Infernal Council
A multi-agent AI tribunal that evaluates products and strategic decisions by simulating seven extreme archetypes of human desire.
AI Persona OS
AI Persona OS is a comprehensive operating system and workspace framework designed to make Openclaw Skills agents reliable, persistent, and full of personality.
Video Generator Image Free
A powerful AI-driven skill that converts static images into dynamic 1080p MP4 video clips through simple text descriptions.
AI Image to Video Kling
A high-performance AI video generation tool that transforms static images into professional 5-second 1080p MP4 clips using the Kling AI engine.
AI Image to Video Converter
A high-performance cloud rendering skill that converts static images like JPG, PNG, and WEBP into professional 1080p animated videos.
Featured*
