speech

Convert text into spoken audio using the OpenAI Audio API CLI.

Updated Mar 22, 2026

Search Tags:#voice #text-to-speech #audio #openai #batch #tts #speech

Ready to run

npx skills add https://github.com/peteanderson80/skills --skill speech-peteanderson80

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/peteanderson80/skills/tree/main/skills/speech
Command: npx skills add https://github.com/peteanderson80/skills --skill speech-peteanderson80

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts plain text into spoken audio, enabling narrated content, voiceovers, accessibility reads, and automated prompts without manual recording or heavy production.

Core Features & Use Cases

Built-in AI voices for quick narration and product demos
Single and batch speech generation for long scripts or multiple prompts
Deterministic CLI workflow with output formats suitable for video, podcasts, or IVR

Quick Start

Generate speech from your text using the bundled CLI with default 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?▼

Convert text to speech by running the bundled CLI commands, which call the OpenAI Audio API to generate spoken audio from your input text using built-in AI voices.

Can I generate voiceovers for multiple scripts in a single batch?▼

Yes, batch speech generation is supported. Use the speak-batch command to process long scripts or multiple prompts simultaneously, with built-in rate limiting and retry logic for reliable output.

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

Yes, an OPENAI_API_KEY is required. You must configure this environment variable to authenticate your requests when converting text into spoken audio through the OpenAI Audio API.

What is the character limit for text-to-speech requests with OpenAI voices?▼

Text-to-speech requests have a 4096-character input limit per request. For longer narration or voiceover scripts, split your text into smaller chunks or use the batch generation command.

What audio formats can I generate for IVR prompts and product demos?▼

The skill supports various output formats suitable for video, podcasts, IVR prompts, and product demos, allowing you to generate natural AI speech tailored to your specific content delivery needs.

Are there built-in AI voices available for narration without manual recording?▼

Yes, built-in AI voices are included. You can select from these predefined voices to quickly generate narration, accessibility reads, or automated prompts without needing manual recording or heavy production.