speech

Convert text into natural-sounding mp3 speech audio via the bundled CLI.

Updated Feb 24, 2026
One-click install
npx skills add https://github.com/ollieb89/.codex --skill speech-ollieb89
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/ollieb89/.codex/tree/main/skills/.curated/speech
Command: npx skills add https://github.com/ollieb89/.codex --skill speech-ollieb89

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts written text into natural-sounding speech audio for narration, prompts, or accessibility reads, enabling quick audio generation without manual recording.

Core Features & Use Cases

  • Single-text to speech: generate one audio clip from a user-provided text.
  • Batch speech generation: process multiple prompts efficiently via the bundled CLI.
  • Deterministic runs: use the included CLI to produce reproducible outputs with built-in voices and a defined workflow.

Quick Start

Run the bundled CLI to convert input text into speech audio.

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 audio for accessibility workflows?

Text-to-speech conversion transforms written text into natural-sounding mp3 audio for narration or accessibility reads. This Skill processes single clips or batch runs using the bundled CLI script to generate deterministic output.

Can I batch generate voice audio from multiple text prompts?

Batch speech generation processes multiple text prompts efficiently via the bundled CLI script. It enables reproducible outputs across projects, product demos, and IVR prompts through a deterministic workflow.

Do I need an OpenAI API key to generate text-to-speech output?

Text-to-speech audio generation requires an OPENAI_API_KEY for live calls. The Skill depends on the OpenAI platform to synthesize natural-sounding voice audio from input text.

What is the character limit for text-to-speech audio generation?

Text-to-speech input is limited to 4096 characters per generation. The Skill enforces this constraint and outputs a default mp3 audio file from the provided text.

What's the best way to automate IVR prompt generation from text?

Automating IVR prompt generation uses the bundled CLI script to convert text into speech audio with deterministic output. This approach handles batch runs efficiently while producing reproducible mp3 files.

Does text-to-speech output support audio formats other than mp3?

Text-to-speech generation defaults to mp3 output format. The Skill uses the bundled CLI script for deterministic audio output, producing mp3 files from input text up to 4096 characters.