Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; ru...
Initial release of the speech skill. - Provides text-to-speech narration, voiceover, and batch speech generation using the OpenAI Audio API and bundled CLI. - Supports single or batch audio generation workflows with clear decision logic. - Covers default voice/model selection, instruction formatting, file conventions, and dependency setup. - Enforces environment checks, API key requirements, and output organization. - Includes comprehensive instruction on user input augmentation and delivery customization. - References sample templates and modules for common use cases (narration, IVR, accessibility, etc.).