← Back to Skills Marketplace
OpenAI TTS
by
Mark Pors 🦖
· GitHub ↗
· v1.0.0
8103
Downloads
6
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install openai-tts
Description
Text-to-speech via OpenAI Audio Speech API.
Usage Guidance
Install this only if you are comfortable sending the text you provide to OpenAI for speech generation. Avoid using it for secrets or confidential content unless that is allowed in your environment, and note that using --out writes the generated audio to the path you choose.
Capability Analysis
Type: OpenClaw Skill
Name: openai-tts
Version: 1.0.0
The skill bundle is benign. The `SKILL.md` provides clear, descriptive instructions without any prompt injection attempts. The `scripts/speak.sh` script correctly interacts with the legitimate OpenAI TTS API endpoint (`https://api.openai.com/v1/audio/speech`), uses the `OPENAI_API_KEY` as expected, and safely escapes user input for the JSON payload using `jq -Rs .`. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, or obfuscation.
Capability Assessment
Credentials
Network access to api.openai.com and use of OPENAI_API_KEY are proportionate for a cloud TTS wrapper; there is no evidence of unrelated host inspection, remote code execution, or broad local data access.
Install Mechanism
The metadata declares curl and OPENAI_API_KEY, while the script also depends on jq for JSON escaping; this is an operational dependency gap, not a security escalation.
Instruction Scope
The documentation names the OpenAI API and endpoint, but it does not prominently warn users that all input text is transmitted off-device; this is purpose-aligned but worth clearer disclosure.
Persistence & Privilege
The only persistence is a user-directed --out path for the generated audio file and the documented optional API-key configuration; there are no services, hooks, scheduled tasks, or privilege escalation mechanisms.
Purpose & Capability
The declared purpose is text-to-speech via OpenAI's Audio Speech API, and the script implements that by sending the provided text, model, voice, format, and speed to the documented OpenAI endpoint.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openai-tts - After installation, invoke the skill by name or use
/openai-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - text-to-speech via OpenAI API with 6 voice options
Metadata
Frequently Asked Questions
What is OpenAI TTS?
Text-to-speech via OpenAI Audio Speech API. It is an AI Agent Skill for Claude Code / OpenClaw, with 8103 downloads so far.
How do I install OpenAI TTS?
Run "/install openai-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenAI TTS free?
Yes, OpenAI TTS is completely free (open-source). You can download, install and use it at no cost.
Which platforms does OpenAI TTS support?
OpenAI TTS is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenAI TTS?
It is built and maintained by Mark Pors 🦖 (@pors); the current version is v1.0.0.
More Skills