tts-prompter

Crafts structured text-to-speech prompts separating style instructions from spoken text.

Updated Sep 16, 2026
One-click install
npx skills add https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills --skill tts-prompter-military-veteran-team-lpt-realty
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tts-prompter
Source: https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills/tree/main/skills/tts-prompter
Command: npx skills add https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills --skill tts-prompter-military-veteran-team-lpt-realty

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Generating natural, expressive text-to-speech audio is unpredictable when prompts mix style directions with the script, causing wrong languages, flat delivery, or tags being read aloud. This Skill provides a proven prompting framework that produces controlled, high-quality TTS output. ## Core Features & Use Cases - Prompt Formula: Enforces the {Style Instructions}: {Spoken Text} structure, separating director instructions from the script with a colon. - Tag Usage Rules: Defines which markup tags work inside spoken text (non-speech sounds, local style shifts, pauses) and which emotional tags must never be used. - Voice & Language Catalog: Includes 30 prebuilt voices with character descriptions and 80+ supported languages with measured speech rates for timing narration against video budgets. - Use Case: When generating multilingual voiceover for a video, use this Skill to write a prompt that specifies accent and emotion in English instructions, places the script in the target language, and sizes the text to the clip duration using the rate table. ## Quick Start Read the tts-prompter skill and generate a TTS prompt for a 30-second excited English product announcement with a laughing intro.

Frequently Asked Questions about tts-prompter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a good text-to-speech prompt?

Structure the prompt as style instructions, a colon, then the spoken text. Write the style instructions in English describing language, accent, emotion, and situation, and write the spoken text in the exact target language you want spoken.

How do I add emotions like laughing or sighing to TTS audio?

Place non-speech sound tags like [laughing], [sigh], or [gasp] inside the spoken text where the sound should occur. Alternatively, describe the emotion in the style instructions before the colon and add breath markers in the text.

Why does the TTS engine read my emotion tags out loud?

Emotional adjective tags like [scared] or [excitedly] are read as literal words by the engine. Move emotional descriptions into the style instructions before the colon and reserve bracket tags for non-speech sounds, local style shifts, and pauses.

How do I generate TTS in multiple languages or mixed languages?

Write the spoken text exactly in the target language or language mix, and explicitly state the mixed-language requirement in the English style instructions. The language_code parameter only hints at the regional voice model and does not force output language.

How do I fit TTS narration into a fixed video duration?

Use the Rate column in the language catalog, which gives average words or characters spoken per second, to size your script against the time budget. Note that delivery style can shift the actual rate by roughly 25 percent.