scaffold-audio-voice

This Skill generates voice audio from text by feeding project-specific style guides and character narratives as context into OpenAI TTS. It processes document-driven or freeform input, allowing voice selection and speed adjustment to align with the established narrative tone.

Yes, you can use OpenAI TTS for narrative text-to-speech by providing design documents as context. The Skill extracts project-specific style guidelines and character narratives from these documents to ensure the generated audio performance matches the game's intended mood.

For context-aware voice synthesis in game development, you need the OpenAI dependency configured for the TTS API. You must also provide project-specific style guides, character narratives, or design documents to inform the vocal performance, alongside your target dialogue text.

Create character-directed voice lines using OpenAI TTS by providing your dialogue text and character instructions to this Skill. It supports character-directed instructions and voice selection, updating an audio index file automatically upon successful generation to keep your project assets organized.

Yes, text-to-speech audio generation updates an audio index file automatically upon successful creation. This ensures that newly generated voice lines and character audio assets are tracked and cataloged within your project's directory structure.