speech

Name: speech
Availability: InStock
Author: shirulot

Generate spoken audio from text using the OpenAI Audio API.

Updated Jul 6, 2026

Search Tags:#audio #openai #tts #voiceover #narration #speech

Ready to run

npx skills add https://github.com/shirulot/codex-skill --skill speech-shirulot

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/shirulot/codex-skill/tree/main/speech
Command: npx skills add https://github.com/shirulot/codex-skill --skill speech-shirulot

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the challenge of creating high-quality, consistent spoken audio for product demos, accessibility reads, and IVR systems without needing professional recording equipment.

Core Features & Use Cases

Batch Audio Generation: Efficiently convert large sets of text prompts into audio files using a JSONL-based workflow.
Style Control: Apply specific voice affects, pacing, and emotional tones to ensure the output matches your brand or project requirements.
Use Case: Quickly generate a full suite of IVR phone prompts or a narrated walkthrough for a software product demo with consistent voice quality.

Quick Start

Use the speech skill to generate an audio file from the text provided in the current context using the cedar voice.

Frequently Asked Questions about speech

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

FAQPage Schema

Can I process multiple text prompts for batch audio generation?▼

Batch audio generation is supported by processing text prompts formatted as a JSONL file. This workflow efficiently converts large sets of text prompts into individual audio files using the OpenAI Audio API.

Do I need an OpenAI API key to run text to speech generation?▼

Yes, text to speech generation requires the openai Python package installed and a valid OPENAI_API_KEY environment variable configured. These prerequisites are necessary to authenticate and execute requests to the OpenAI Audio API.

What is the best way to create consistent IVR phone prompts with AI narration?▼

The best way to create consistent IVR phone prompts is applying style control parameters like specific voice affects, pacing, and emotional tones. This ensures the AI narration matches your brand requirements across a full suite of generated audio files.

Does this text to speech skill support custom voice speed and delivery instructions?▼

Yes, the text to speech skill supports configurable voice, speed, and delivery instructions. You can apply specific voice affects and pacing to ensure the generated spoken audio matches your project requirements.