domains / families / media / speech

speech

authentic

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; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

When to use

• Generate a single spoken clip from text
• Generate a batch of prompts (many lines, many files)

When not to use

• custom voice creation

Skill page

Source