skills.rest
openai
openaiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

speech

Generate spoken audio from text via the OpenAI Audio API.

24.7k|1.7k|Updated Nov 25, 2025
Search Tags:#text-to-speech#audio generation#tts#voiceover#narration#speech
One-click install
npx skills add https://github.com/openai/skills --skill speech-openai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/openai/skills/tree/main/skills/.curated/speech
Command: npx skills add https://github.com/openai/skills --skill speech-openai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables the generation of spoken audio from text, perfect for narration, voiceovers, accessibility features, and automated audio prompts.

Core Features & Use Cases

  • Text-to-Speech Narration: Convert written content into audio with various voices and styles.
  • Batch Audio Generation: Process multiple text inputs efficiently for prompts or audio clips.
  • Use Case: Generate voiceovers for a product demo video, create audio versions of articles for accessibility, or produce a set of IVR prompts for a customer service line.

Quick Start

Use the speech skill to generate an audio file named 'welcome.mp3' from the text 'Welcome to our service.'.

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?▼

Yes, batch text-to-speech generation is supported, allowing you to process multiple text inputs efficiently. This feature is ideal for producing a set of IVR prompts, automated audio clips, or multiple voiceover files simultaneously via the bundled CLI script.

Do I need an OPENAI_API_KEY to generate audio from text?▼

Yes, you must provide a valid OPENAI_API_KEY to perform live API calls for text-to-speech generation. The Skill relies on this key to authenticate requests to the OpenAI Audio API and generate your spoken audio files.

What are the limitations when using text-to-speech for narration?▼

The primary limitations for text-to-speech narration include adhering to input length and rate limits imposed by the OpenAI Audio API. Users must manage large text inputs or frequent batch processing requests within these defined API constraints.

Can I customize voices for voiceover generation?▼

Yes, you can customize voice parameters for voiceover generation when converting text to speech. This allows you to select various voices and styles to match the specific needs of your product demos, articles, or accessibility reads.

Related Skills

Explore More Content & Communication Skills→
moltis-orgmoltis-org
2.8k

openai-whisper-api

Transcribe audio files via OpenAI's Whisper API endpoint.

Official
Intermediate
hoanghd218hoanghd218
3

mkt-video-script-to-mp3

Convert video scripts into MP3 voiceover audio via the MiniMax TTS API.

Community
Intermediate
wpgauravwpgaurav
14

11labs

Convert long-form text into ElevenLabs V3 scripts with emotional tags and 5,000-character blocks.

Community
Intermediate
MOODMNKY-LLCMOODMNKY-LLC

sherpa-onnx-tts

Converts text to speech offline using sherpa-onnx runtime and voice models.

Community
Intermediate