# Text To Speech

> Convert text to natural speech with Inworld TTS, ElevenLabs, DIA TTS, Kokoro, Chatterbox, and more via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (premium, 22+ voices, 32 languages), DIA TTS (conversational), Kokoro TTS, Chatterbox, Higgs Audio, VibeVoice (podcasts). Capabilities: text-to-speech, voice cloning, multi-speaker dialogue, podcast generation, expressive speech, emotion/delivery steering, character voices. Use for: voiceovers, audiobooks, podcasts, accessibility, video narration, IVR, voice assistants, gaming characters, avatar audio. Triggers: text to speech, tts, voice generation, ai voice, speech synthesis, voice over, generate speech, ai narrator, voice cloning, text to audio, elevenlabs, eleven labs, voice ai, ai voiceover, speech generator, natural voice, inworld, inworld tts, character voice, game voice, npc voice

Source: https://skillsagentes.com/skills/skills-101/superpowers/text-to-speech
Repository: https://github.com/skills-101/superpowers
Author: skills-101
License: not specified
Updated: hace 11 días
Context cost: 231 tok installed, 1.7k tok once triggered, 1.7k tok with every bundled file
Bundle: 1 file, 7 KB
Permissions requested: bash(belt *)

## Install

```bash
npx -y skills add skills-101/superpowers --skill text-to-speech --agent claude-code
```

## What it does

- Convierte texto en voz natural usando modelos como Inworld TTS-2, ElevenLabs, DIA TTS, Kokoro, Chatterbox, Higgs Audio y VibeVoice vía la CLI de inference.sh (belt)
- Permite clonación de voz, diálogos multi-hablante, generación de podcasts y steering de emoción/entrega con [corchetes]
- Ejecuta modelos con `belt app run <app-id> --input '{...}'` y permite listar apps de audio con `belt app list --category audio`
- Combina audio generado con video de avatar (p. ej. P-Video-Avatar, OmniHuman) para crear vídeos de cabeza parlante

## Use it when

- Necesitas generar voiceovers, audiolibros, podcasts o narración de vídeo
- Quieres voces de personajes para juegos/NPCs con steering de emoción (Inworld TTS-2)
- Necesitas respuestas de baja latencia para IA conversacional o IVR
- Vas a crear vídeos de avatar parlante y necesitas la pista de audio

## What triggers it

- "Convierte este texto en voz con Kokoro TTS"
- "Genera una narración con emoción usando Inworld TTS-2"
- "Crea un episodio de podcast a partir de este guion con VibeVoice"
- "Necesito una voz de baja latencia para mi asistente conversacional"

## Before you install

- Requiere la CLI de inference.sh (belt) instalada y haber ejecutado `belt login`.
- Needs on PATH: npx

## Files

- SKILL.md — 7 KB

## SKILL.md

Not reproduced here. Read it at https://github.com/skills-101/superpowers/blob/main/tools/audio/text-to-speech/SKILL.md

---

Skills Agentes — https://skillsagentes.com/skills/skills-101/superpowers/text-to-speech