Speech

Turns OpenAI's text-to-speech API into a Claude skill so you can generate narration or voiceovers without leaving your workflow. You feed it text, it hands back audio files using OpenAI's built-in voices. The skill comes from OpenAI's official repository, which suggests it's a reference implementation rather than something heavily customized. Most useful when you need quick audio for explainer videos, lecture content, or prototyping voice interfaces. Not much configuration shown here, so expect a straightforward wrapper around the API rather than a full production audio pipeline.

Install to Claude Code

npx -y skills add nexu-io/open-design --skill speech --agent claude-code