speech

Name: speech
Availability: InStock
Author: Keni

Synthesize spoken audio from text using the OpenAI Audio API.

1|Updated Mar 27, 2026

Search Tags:#accessibility #text-to-speech #tts #batch-processing #speech #voices #audio-api

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Turning text into spoken audio for narration, accessibility reads, IVR prompts, and product demos, eliminating manual voiceover work.

Core Features & Use Cases

Generate a single spoken clip from text using built-in voices and safe defaults.
Batch generate multiple audio clips from prompts or files, with per-job overrides and rate-limited batching.
Validate inputs, require OPENAI_API_KEY for live calls, and support output in mp3/wav and related formats.

Quick Start

Run the bundled CLI to generate speech from input text using 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?▼

To convert text to speech, the Skill synthesizes spoken audio from text using the OpenAI Audio API with built-in voices, enforcing input length and safe defaults. It requires an active OPENAI_API_KEY for live generation calls.

Can I batch generate multiple text-to-speech audio clips from a file?▼

Yes, you can batch generate multiple text-to-speech audio clips from prompts or files. The process supports per-job overrides and applies rate-limited batching to safely manage multiple speech synthesis jobs.

What audio formats are supported when synthesizing speech from text?▼

When synthesizing speech from text, the supported output formats include mp3 and wav. The Skill lists all supported voices and output formats while validating inputs before generating the audio.

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

Yes, you need an OPENAI_API_KEY to generate text-to-speech narration. The Skill requires this key for live API calls and validates its presence before attempting to synthesize spoken audio.

What is the best way to automate voiceover generation for product demos?▼

The best way to automate voiceover generation for product demos is using a bundled CLI with built-in voices and safe defaults. This eliminates manual voiceover work by synthesizing spoken audio directly from your text scripts.

Are there input length limitations when generating spoken audio from text?▼

Yes, there are input length limitations when generating spoken audio from text. The Skill enforces input length validation and safe defaults to prevent errors during the audio synthesis process with the OpenAI Audio API.