Speech generation
Generates text-to-speech narration, voiceovers, accessibility reads, and batches with the OpenAI Audio API.
OpenAI
What this skill does
Use for speech generation; the catalog skill says live calls require OPENAI_API_KEY and custom voice creation is out of scope.
Where, why and how to use it
Use when the requested deliverable is spoken audio. Collect exact text, voice, delivery, and format; verify the returned audio. A paid API call requires explicit user authorization and configured key.
Official historical catalog entry. No voice was generated. Do not imply voice cloning/custom voice support.
Source location
openai/skills:skills/.curated/speech/SKILL.md
Compatibility and setup
Requires OpenAI-specific API workflow; not portable without adapter and credentials.
OpenAI API key, SDK/runtime, and possible paid usage; none supplied or called here.
Boundaries
Do not make paid calls without authorization, expose keys, alter approved text, or claim custom voice support.
Source version
openai/skills main; deprecated; unpinned. Reference checked 2026-10-14. Source verification does not mean this skill is installed, its connector is available or its service entitlement active.
Example instruction
Prepare a 30-second narration from this approved script and return the audio for review.