Setup & Installation
npx skills add https://github.com/openai/skills --skill speech
https://github.com/openai/skills/tree/main/skills/.curated/speech
View on GitHubWhat This Skill Does
Generates spoken audio from text using the OpenAI Audio API. Supports single clips and batch jobs, with built-in voices and optional delivery instructions for tone, pacing, and emphasis. Uses a bundled CLI for reproducible runs.
The bundled CLI handles batching, rate limiting, and output organization so you don't have to wire up the API manually each time.
When to use it
- Adding narration to a product demo video
- Generating IVR phone prompts in bulk from a JSONL file
- Creating accessibility audio reads for UI text
- Producing voiceover clips for explainer slides
- Iterating on delivery style with single-change voice tweaks