Skip to content
/speechOfficial

Generate narrated audio from text using OpenAI with voice style, pacing, and format control.

AIOpenAIAudioTTS· 1 min read

Quick import: Download the .md file and save it to .claude/commands/ (Claude Code), .cursorrules (Cursor), or paste as a system prompt in ChatGPT, Gemini, or any LLM API.

#What it does

The speech skill generates spoken audio from text using the OpenAI text-to-speech API. It handles voice selection, pacing control, output format configuration, and produces narrated audio suitable for podcasts, voiceovers, accessibility, and content creation.

#How to use

bash
$speech
Generate spoken audio for this text with the right voice style, pacing, and output format.

#Capabilities

  • Convert text to natural-sounding speech
  • Select from multiple voice styles
  • Control pacing and delivery speed
  • Output in multiple audio formats
  • Batch generation for longer content

#Use cases

  • Podcast narration
  • Video voiceovers
  • Accessibility audio for written content
  • Audio previews for written drafts
  • Automated announcements and notifications

#Environment

  • OPENAI_API_KEY must be set for live API calls

This skill is from the OpenAI Skills Catalog.

OpenAI·
View all skills