TTS Skill - Text-to-Speech Synthesis

Name: TTS Skill - Text-to-Speech Synthesis
Availability: InStock
Author: powerfulmoves

Synthesize text into speech using multiple TTS engines and voice personas.

1|Updated Nov 7, 2025

Search Tags:#text-to-speech #podcast #audio generation #tts #voice synthesis #voice personas

Ready to run

npx skills add https://github.com/POWERFULMOVES/PMOVES-BoTZ --skill tts-skill-text-to-speech-synthesis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: TTS Skill - Text-to-Speech Synthesis
Source: https://github.com/POWERFULMOVES/PMOVES-BoTZ/tree/main/features/agent_sdk/slices/tts
Command: npx skills add https://github.com/POWERFULMOVES/PMOVES-BoTZ --skill tts-skill-text-to-speech-synthesis

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill transforms written text into natural-sounding speech, enabling dynamic audio content creation and accessibility.

Core Features & Use Cases

Text-to-Speech Synthesis: Convert any text into audio using various AI voice personas.
Voice Personas: Choose from distinct voices like HOST, ARCHITECT, and OPS for different tones and styles.
Punctuation Engineering: Control prosody and pauses for more natural-sounding narration.
Voice Cloning: Create custom voices from reference audio.
Multi-Speaker Content: Generate podcast-style conversations with multiple voices.
Use Case: Automatically generate audio narration for your documentation, create engaging podcast episodes with distinct characters, or build voice-enabled features for your applications.

Quick Start

Use the TTS skill to synthesize the text "Hello, world!" with the HOST persona.

Frequently Asked Questions about TTS Skill - Text-to-Speech Synthesis

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

FAQPage Schema

How do I convert text to speech using AI voice personas?▼

To convert text to speech, this skill synthesizes written content using AI-powered engines and predefined voice personas like HOST, ARCHITECT, and OPS. You simply provide the text and select a persona to generate audio with distinct tones and styles.

Can I create multi-speaker podcast audio from text?▼

Yes, you can generate multi-speaker podcast content by assigning different AI voice personas to text segments. The skill orchestrates multiple voices to simulate dynamic conversations and character interactions.

Does text-to-speech synthesis support custom voice cloning?▼

Custom voice cloning is supported through reference audio integration. The skill analyzes reference audio files to create custom voice personas, allowing you to generate speech that matches specific vocal characteristics.

What is punctuation engineering for text-to-speech prosody control?▼

Punctuation engineering manipulates text markers to control speech prosody and pauses. This technique allows you to fine-tune the rhythm, pacing, and natural-sounding delivery of AI-generated audio narration.

Which TTS engines can I use for voice synthesis?▼

The skill integrates with multiple TTS engines including Kokoro, Fish Speech, IndexTTS2, ElevenLabs, and OpenAI TTS. This allows flexible configuration across different platforms for pitch, speed, and emotion control.