A high-performance text-to-speech engine leveraging OpenAI's API to generate lifelike spoken audio from text.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openai-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 openai-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 OpenAI TTS?
The openai-tts skill is a specialized utility designed to interface with the OpenAI Audio Speech API. It enables developers and AI agents to convert text strings into high-quality spoken audio using diverse voice profiles such as alloy, echo, and nova. By incorporating this into the broader ecosystem of Openclaw Skills, users can automate the production of audio content, voice notifications, or accessible feedback loops within their local environment.
This skill supports both the tts-1 model for low-latency applications and the tts-1-hd model for high-fidelity audio output. It is built to be lightweight, requiring only curl and an API key, making it a highly portable solution for speech synthesis tasks.
OpenAI TTS Use Cases
- Creating automated voice responses for CLI-based AI assistants.
- Generating voiceovers for video content or presentations using multiple distinct voice profiles.
- Converting written documentation or notes into audio files for on-the-go listening.
- Providing accessibility features through real-time text-to-speech conversion in scripts.
How OpenAI TTS Works
- The user provides a text input via the speak.sh script along with optional flags for voice, speed, and format.
- The skill validates the presence of the OPENAI_API_KEY environment variable or configuration entry.
- A POST request is sent to the OpenAI v1/audio/speech endpoint using curl.
- The OpenAI model processes the text and returns an encoded audio stream (defaulting to MP3).
- The skill saves the audio to a specified file path or outputs it directly to stdout for immediate consumption.
OpenAI TTS Setup
To use this skill, ensure you have curl installed and a valid OpenAI API key.
# Export your API key
export OPENAI_API_KEY="sk-..."
# Run the speech script
./scripts/speak.sh "Hello, world!" --out output.mp3
Alternatively, you can add your credentials to the Openclaw Skills configuration file at ~/.clawdbot/clawdbot.json to avoid manual exports.
OpenAI TTS Data Schema & Taxonomy
The skill utilizes specific parameters to control the audio generation process. Below is the schema for available options:
| Parameter | Description | Valid Options |
|---|---|---|
| model | The AI model used for synthesis | tts-1, tts-1-hd |
| voice | The persona of the generated audio | alloy, echo, fable, onyx, nova, shimmer |
| format | The audio file container | mp3, opus, aac, flac, wav, pcm |
| speed | The pace of the generated speech | 0.25 to 4.0 |
OpenAI TTS Advanced Features
- Support for high-definition audio via the tts-1-hd model for professional-grade output.
- Multi-format exports including lossless FLAC and web-optimized OPUS or AAC.
- Adjustable playback speed for fine-tuning the delivery of technical or dense information.
- Seamless integration into automated pipelines via standard CLI pipes and redirects.
- Secure configuration management through the centralized Openclaw Skills settings.
SKILL.md
Loading
Related Openclaw Skills
Crucial Conversations Coach
An AI-powered executive coach that applies the Tools for Talking When Stakes Are High methodology to help users navigate emotional and controversial discussions.
Clawdbot Release Check
A specialized utility that monitors GitHub for new Clawdbot releases and provides non-intrusive notifications including release highlights.
B2B First Ten (The Hunt)
An expert AI advisor that helps founders secure their first 10 B2B customers using unscalable, high-hustle tactics based on research from top tech companies.
Germanic
Germanic is a specialized tool for enforcing strict schema contracts on JSON data and compiling it into secure, injection-resistant binary .grm files.
Paperzilla CLI (pz)
A command-line interface for Paperzilla that enables seamless discovery and filtering of high-signal academic papers for researchers.
Research Assistant
A high-efficiency research sub-agent that utilizes the Gemini CLI to perform exhaustive topic deep dives without exhausting your primary model tokens.
Featured*
