speech

Convert text to spoken audio via the OpenAI Audio API.

1|Updated Jul 1, 2026
One-click install
npx skills add https://github.com/whopointer/enterprise-office-agent --skill speech-whopointer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/whopointer/enterprise-office-agent/tree/main/skills/speech
Command: npx skills add https://github.com/whopointer/enterprise-office-agent --skill speech-whopointer

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill converts written text into spoken audio, providing a solution for creating narrations, voiceovers, and accessibility reads. It utilizes the OpenAI Audio API for high-quality audio generation.

Core Features & Use Cases

  • Text-to-Speech: Convert text into spoken audio in various voices and styles.
  • Voice Customization: Select from a range of built-in voices and adjust parameters like speed and tone.
  • Use Case: Use this Skill to create voice narration for videos, generate audio prompts for applications, or offer accessibility features for documents.

Quick Start

Run the script with python3 scripts/text_to_speech.py --input "Welcome to the demo." --voice cedar --out welcome.mp3

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 spoken audio for a voiceover?

You can convert text to spoken audio by running a Python script that sends your input text to the OpenAI Audio API. This generates high-quality voiceover files by processing the text and saving the resulting audio output as an MP3 file.

Can I customize the voice style and pacing for text-to-speech generation?

Yes, text-to-speech generation supports custom voice styles and pacing adjustments. You can select from a variety of built-in voices and modify parameters like speed and tone to match your specific narration or accessibility requirements.

Do I need an OpenAI API key to generate audio narration?

Yes, you need an OpenAI API key to generate audio narration, as the script makes live calls to the OpenAI Audio API. You also need Python installed in your environment to execute the text-to-speech script successfully.

What is the best way to create audio accessibility reads from text?

The best way to create audio accessibility reads is using a text-to-speech tool that converts written documents into spoken audio. This approach leverages the OpenAI Audio API to provide clear, customizable voices for users requiring auditory assistance.

How do I run a Python script for text-to-speech conversion?

You run a Python script for text-to-speech conversion by executing the file with Python3, passing your text input, desired voice, and output filename as command-line arguments. The script processes these parameters to generate your audio file.