skills.rest
guardian-intelligence
guardian-intelligenceOFFICIAL
Explore all skills by this author →
Website𝕏@guardians_llcGitHub

elevenlabs-tts

Format text with audio tags and pronunciation controls for ElevenLabs TTS models.

Updated Aug 23, 2026
Search Tags:#normalization#elevenlabs#tts#pronunciation#text-formatting#audio-tags
One-click install
npx skills add https://github.com/guardian-intelligence/guardian-core --skill elevenlabs-tts-guardian-intelligence
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-tts
Source: https://github.com/guardian-intelligence/guardian-core/tree/main/.claude/skills/elevenlabs-tts
Command: npx skills add https://github.com/guardian-intelligence/guardian-core --skill elevenlabs-tts-guardian-intelligence

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill formats plain text into ElevenLabs TTS-ready input, enabling expressive delivery with audio tags, pauses, pronunciation controls, and model-specific nuances.

Core Features & Use Cases

  • Audio tagging: insert model-compatible audio tags to convey emotion and pacing.
  • Pronunciation control: apply phoneme tags, alias mappings, and dictionaries to improve pronunciation.
  • Text normalization: normalize numbers, dates, currencies, and abbreviations for natural speech.
  • Use Case: prepare audiobook narration, dialogue formatting, or scripted scenes across ElevenLabs models (v3, v2, v2.5), with multi-speaker capabilities when applicable.

Quick Start

Take a short paragraph and format it for ElevenLabs TTS by adding appropriate tags and pronunciation cues.

Frequently Asked Questions about elevenlabs-tts

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

FAQPage Schema
How do I format text for ElevenLabs TTS to control pronunciation and pacing?▼

To format text for ElevenLabs TTS, you apply audio tags for pacing, phoneme tags for pronunciation control, and normalize numbers or dates to ensure expressive delivery and natural speech synthesis.

What is text normalization for TTS and when do I need it?▼

Text normalization for TTS converts numbers, dates, currencies, and abbreviations into spoken-language equivalents. You need it to prevent robotic mispronunciations and ensure natural delivery in audio narration.

How do I add emotion and pauses using audio tags in ElevenLabs v3?▼

You add emotion and pauses by inserting model-compatible audio tags directly into your script text. ElevenLabs v3 supports specific tags to convey expressive delivery and pacing across narration workflows.

Can I use phoneme tags and alias mappings for pronunciation control in TTS scripts?▼

Yes, you can apply phoneme tags, alias mappings, and pronunciation dictionaries to control exactly how specific words are spoken, ensuring accurate pronunciation across ElevenLabs v3 and v2 models.

Does this TTS formatting approach work for multi-speaker dialogue and audiobook narration?▼

Yes, this formatting approach supports multi-speaker dialogue and audiobook narration by structuring scripts with appropriate audio tags and normalization for clear, expressive delivery across supported models.

Why does ElevenLabs TTS mispronounce abbreviations and how do I fix it?▼

ElevenLabs TTS mispronounces abbreviations due to raw text normalization failures. You fix it by applying pronunciation dictionaries and alias mappings to format the input text before synthesis.

Related Skills

Explore More Content & Communication Skills→
syusamasyusama
4

podcast-generation

Convert text content into a structured podcast script and synthesize dialogue into an MP3 audio file.

Community
Intermediate
vm0-aivm0-ai
76

elevenlabs

Convert text to speech using ElevenLabs voices and v1 endpoints.

Official
Intermediate
akrindevakrindev
4

gemini-tts

Generates speech from text using Google Gemini TTS models via Python scripts.

Community
Intermediate
Probably-GroupProbably-Group
3

text-to-speech

Generate local text-to-speech audio from sanitized text using Kokoro TTS.

Official
Advanced