speech

speech is an Open Design catalogue entry for a skill that generates spoken audio from text using OpenAI's API with its built-in voices. It addresses the need for quick, natural-sounding voiceover without recording talent or manual audio editing, turning written scripts into narrated audio tracks on demand. Typical outputs include narrated explainers, lecture audio, and short voiceover tracks.

In this catalogue, the entry is a thin advertisement rather than the executable skill. The SKILL.md describes the capability, lists trigger phrases such as "openai speech", "tts openai", "narrated audio", and "voice over", and points to the upstream source in OpenAI's skills repository. To run the full workflow with its original assets, scripts, and references, users install the upstream bundle from github.com/openai/skills into their active agent's skills directory. Actual synthesis requires access to OpenAI's API; the catalogue entry itself contains no code or credentials.

Intended users are content creators, educators, and product teams who need narration or voiceover generated from text. Typical use cases include producing narrated explainer videos, generating lecture or course audio, and adding quick voiceover tracks to media, once the upstream bundle and OpenAI API access are configured.