# Ai Voice Cloning

> AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (22+ premium voices, 32 languages), Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation, voice transformation, delivery mode control, character voices. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility, gaming NPCs, avatar audio, UGC. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs, eleven labs, natural voice, realistic speech, voice ai, voice changer, inworld, inworld tts, character voice, npc voice

Source: https://skillsagentes.com/skills/skills-101/superpowers/ai-voice-cloning
Repository: https://github.com/skills-101/superpowers
Author: skills-101
License: not specified
Updated: hace 11 días
Context cost: 207 tok installed, 2.5k tok once triggered, 2.5k tok with every bundled file
Bundle: 1 file, 10 KB
Permissions requested: bash(belt *)

## Install

```bash
npx -y skills add skills-101/superpowers --skill ai-voice-cloning --agent claude-code
```

## What it does

- Genera voces artificiales naturales mediante la CLI belt (inference.sh) usando modelos como Inworld TTS-2, ElevenLabs, Kokoro, DIA, Chatterbox, Higgs y VibeVoice
- Permite controlar emoción, no-verbales y modo de entrega con marcadores entre corchetes como [whisper] o [excited]
- Soporta múltiples voces, idiomas, acentos, velocidad y puntuación para pacing
- Combina voz con video o avatares mediante media-merger y omnihuman-1-5

## Use it when

- Necesitas generar voiceovers, audiolibros, podcasts o narración de video
- Requieres voces de personajes o NPCs con emociones y control de entrega
- Necesitas contenido de accesibilidad, IVR o localización de contenido con voz
- Quieres crear diálogos multi-voz o narración de formato largo por fragmentos

## What triggers it

- "Genera una narración de audiolibro con voz bf_emma a velocidad 0.9"
- "Crea un diálogo entre dos voces usando kokoro-tts"
- "Genera una voz de personaje emocionada con Inworld TTS-2"
- "Añade un voiceover profesional a este video"

## Before you install

- Requiere instalar la CLI belt de inference.sh y ejecutar belt login.
- Needs on PATH: npx

## Files

- SKILL.md — 10 KB

## SKILL.md

Not reproduced here. Read it at https://github.com/skills-101/superpowers/blob/main/tools/audio/ai-voice-cloning/SKILL.md

---

Skills Agentes — https://skillsagentes.com/skills/skills-101/superpowers/ai-voice-cloning