speech

Generate speech audio from text using the OpenAI Audio API.

2|1|Updated Apr 2, 2026

Search Tags:#cli #text-to-speech #audio #openai #tts #speech #voices

Ready to run

npx skills add https://github.com/Sacred-G/oh-my-claw --skill speech-sacred-g

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/Sacred-G/oh-my-claw/tree/main/secure-openclaw/skills-main/skills/.curated/speech
Command: npx skills add https://github.com/Sacred-G/oh-my-claw --skill speech-sacred-g

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (scripts/text_to_speech.py) with built-in voices and require OPENAI_API_KEY for live calls. Custom voice creation is out of scope.

Core Features & Use Cases

Generates spoken audio from text using built-in voices via the OpenAI Audio API.
Supports single and batch processing (via JSONL jobs) and accessibility reads.
Provides a deterministic CLI-based workflow with input validation, rate limiting, and error handling.

Quick Start

Run the bundled CLI to generate speech audio from input text using the built-in voices.

Frequently Asked Questions about speech

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert text to speech using the OpenAI Audio API?▼

You can convert text to speech by running the bundled CLI script, which automates speech generation using the OpenAI Audio API and outputs common audio formats. It handles input validation and provides built-in voices for single or multi-line text.

Do I need an OPENAI_API_KEY to generate audio from text?▼

Yes, an OPENAI_API_KEY is required for live API calls to the OpenAI Audio API. The Skill needs this key to authenticate speech generation requests and produce audio outputs from your input text.

Can I process multiple text-to-speech jobs in batch?▼

Yes, batch speech generation is supported through JSONL job files. The Skill processes multiple text-to-speech jobs sequentially, handling rate limits and error recovery to ensure all audio outputs are generated successfully.

What limitations exist when using built-in voices for text-to-speech?▼

The main limitation is that custom voice creation is out of scope; you are restricted to the built-in voices provided by the OpenAI Audio API. The Skill also depends on live API calls, meaning rate limits and service availability affect processing.

How does the CLI handle input validation and rate limits for speech generation?▼

The CLI manages input validation and rate limits through a deterministic workflow that validates text before processing and paces API requests to the OpenAI Audio API. It includes error recovery to handle failures during speech generation.