tts

Convert text into speech audio using Kokoro offline or Noiz cloud backends.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/missyouangeled/test-git --skill tts-missyouangeled
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tts
Source: https://github.com/missyouangeled/test-git/tree/main/skills/noizai-tts
Command: npx skills add https://github.com/missyouangeled/test-git --skill tts-missyouangeled

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

Convert text into speech audio for narration, accessibility, and voice-enabled applications across offline Kokoro and cloud Noiz backends.

Core Features & Use Cases

  • Simple TTS with Kokoro (offline) or Noiz (cloud) backends
  • Timeline-accurate rendering for per-segment voice control and SRT alignment
  • Voice cloning, emotion control, and language mapping across backends

Quick Start

Speak text to audio using the TTS CLI with your preferred backend and format.

Frequently Asked Questions about tts

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

FAQPage Schema
How do I convert text to speech with offline and cloud backends?

You can convert text to speech using either the Kokoro offline backend or the Noiz cloud backend. This provides flexible audio generation for narration, dubbing, and accessibility across different deployment environments.

How does timeline-based rendering work for text-to-speech?

Timeline-based rendering enables per-segment voice control and SRT alignment for text-to-speech. This allows precise synchronization of generated speech audio with specific timestamps and individual timeline segments.

Can I use voice cloning and emotion control with Kokoro or Noiz?

Yes, voice cloning and emotion control are supported across both Kokoro and Noiz backends. You can apply emotion control and utilize reference audio support to customize the generated speech output.

Does text-to-speech support cross-language voice mapping?

Yes, cross-language voice mapping is supported with per-segment control during text-to-speech synthesis. This allows you to map voices across different languages while maintaining precise control over individual speech segments.

Do I need an API key for text-to-speech processing?

API key management is required for text-to-speech processing, though an optional guest mode is available. The API key enables access to backend features like cloud Noiz rendering and advanced voice cloning controls.