skills.rest
gabrielkoerich
gabrielkoerichCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

elevenlabs-voices

Consolidate ElevenLabs voice personas and tooling into a reusable skill.

5|Updated Feb 4, 2026
Search Tags:#multilingual#elevenlabs#tts#batch-processing#voice-design#pronunciations
One-click install
npx skills add https://github.com/gabrielkoerich/skills --skill elevenlabs-voices
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-voices
Source: https://github.com/gabrielkoerich/skills/tree/main/elevenlabs-voices
Command: npx skills add https://github.com/gabrielkoerich/skills --skill elevenlabs-voices

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Centralizes ElevenLabs voice personas and tooling into a single, reusable skill to enable scalable TTS production across multilingual contexts.

Core Features & Use Cases

  • 18 predefined personas across 32 languages, enabling quick coverage for diverse audiences.
  • Support for sound effects, batch processing, and voice design to compose rich audio experiences.
  • Local data models (voices.json, pronunciations.json) plus CLI scripts (tts.py, sfx.py, voice-design.py) to produce, test, and integrate voices with agents.

Quick Start

Clone this repository and run ./setup.sh to configure dependencies and API keys for ElevenLabs Voices.

Frequently Asked Questions about elevenlabs-voices

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

FAQPage Schema
How do I generate multilingual text-to-speech audio for batch processing?▼

To generate multilingual text-to-speech audio, this skill provides Python scripts for batch processing across 32 languages, using 18 predefined voice personas to produce scalable TTS output locally.

Can I use ElevenLabs voices with custom pronunciations for agent integration?▼

Yes, you can use ElevenLabs voices with custom pronunciations for agent integration by utilizing the provided pronunciations.json data file alongside the activation workflow to manage and preview voice output.

What is the best way to design custom AI voices for scalable TTS production?▼

The best way to design custom AI voices for scalable TTS is using the included voice-design.py script, which allows you to create and test diverse voice personas within a consolidated, reusable environment.

Does this ElevenLabs voice tool support generating sound effects alongside speech?▼

Yes, this ElevenLabs voice tool supports generating sound effects alongside speech by running the dedicated sfx.py script, enabling you to compose rich audio experiences for multilingual content.

How do I configure an ElevenLabs TTS environment to manage multiple voice personas?▼

You configure an ElevenLabs TTS environment by running the setup.sh script to establish dependencies and API keys, then using the local voices.json file to manage 18 distinct voice personas.

What are the limitations of using predefined TTS voice personas for multilingual content?▼

A limitation of using predefined TTS voice personas is being restricted to the 18 available voices across 32 languages, though you can overcome this by using the custom voice design script for specialized needs.

Related Skills

Explore More Content & Communication Skills→
pinion05pinion05
3

elevenlabs-tts

Generate audio from text using the ElevenLabs API with configurable voices.

Community
Intermediate
modu-aimodu-ai
267

audio-gen

Generate multilingual speech, voice clones, and sound effects via ElevenLabs TTS.

Official
Intermediate
TheArchitectitTheArchitectit
3

audio-gen

Unify text-to-speech, transcription, audio conversion, and editing workflows.

Community
Intermediate
storyclaw-officialstoryclaw-official

elevenlabs-tts

Convert text to ogg_opus speech via the ElevenLabs API.

Official
Intermediate