speech

Convert text into speech audio files using the OpenAI Audio API.

Updated May 11, 2026
One-click install
npx skills add https://github.com/cloudofgeorge/AI-hands --skill speech-cloudofgeorge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/cloudofgeorge/AI-hands/tree/main/skills/speech
Command: npx skills add https://github.com/cloudofgeorge/AI-hands --skill speech-cloudofgeorge

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts text into natural-sounding speech for narration, product demos, accessibility prompts, and other audio outputs, enabling quick audio generation without manual voiceover.

Core Features & Use Cases

  • Single-shot text-to-speech: generate a single audio clip from provided text.
  • Batch generation: produce many clips in one run using the bundled CLI.
  • Built-in voices and defaults: uses Cedar by default, with optional voices and standard formats.
  • End-to-end workflow: supports input collection, instruction augmentation, output formatting, and quality checks.
  • Use cases: narrations for demos, IVR prompts, accessibility reads, or product voiceovers.

Quick Start

Provide the input text and desired voice, then run the bundled CLI to generate an audio file.

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 natural-sounding speech for narration or product demos?

Text-to-speech conversion generates natural-sounding audio clips from input text using built-in voices for narration and product demos. You provide the text and desired voice, then run the bundled CLI to produce an audio file quickly without manual voiceover.

Can I batch generate multiple text-to-speech audio clips in one run?

Batch text-to-speech generation produces many audio clips in one run using the bundled CLI. It supports single-clip generation and batch workflows, enabling efficient output for multiple text inputs without processing each individually.

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

Text-to-speech audio generation requires an OPENAI_API_KEY for live runs. The Skill uses the OpenAI Audio API via the bundled CLI to process input text and produce speech output with built-in voices.

What voices are available for text-to-speech generation?

Text-to-speech generation uses built-in voices with Cedar as the default option. You can specify optional voices and standard formats when providing input text to the bundled CLI for audio output.

Are there input length limits when converting text to speech?

Text-to-speech conversion enforces input length limits on provided text before processing. The bundled CLI validates input length to ensure successful audio generation through the OpenAI Audio API.

What's the best way to create IVR prompts or accessibility audio from text?

Creating IVR prompts and accessibility reads uses text-to-speech conversion with built-in voices and deterministic defaults. The bundled CLI handles input collection, instruction augmentation, output formatting, and quality checks for end-to-end audio generation.