What problem does it solve? Generating natural, expressive text-to-speech audio is unpredictable when prompts mix style directions with the script itself. This Skill provides a proven prompting framework that separates director instructions from spoken text, preventing common failures like tags being read aloud or wrong-language output. ## Core Features & Use Cases - Prompt Formula: Enforces the {Style Instructions}: {Spoken Text} structure with a colon separator, plus multi-speaker dialogue formatting. - Markup Tag Rules: Defines which bracket tags work (non-speech sounds, local style shifts, pauses) and which to avoid (emotional adjectives that get read aloud). - Voice & Language Catalog: Lists 30 prebuilt voices with timbre descriptions and 80+ supported languages with measured speech rates for timing-constrained tasks like video narration and dubbing. - Use Case: You need Brazilian Portuguese narration for a 30-second video. Use the rate table (1.7 words/second for pt-BR) to size the script, pick a voice like Sulafat, and write English style instructions before the colon with Portuguese spoken text after it. ## Quick Start Use the tts-prompter skill to write a TTS prompt for a warm Brazilian Portuguese welcome message with a brief pause before the greeting.
