tts

Convert text into speech using Kokoro or Noiz backends.

526|77|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/NoizAI/skills --skill tts-noizai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tts
Source: https://github.com/NoizAI/skills/tree/main/skills/tts
Command: npx skills add https://github.com/NoizAI/skills --skill tts-noizai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Convert text into speech across local Kokoro and cloud Noiz backends, enabling quick voiceovers and narrated content without external editing.

Core Features & Use Cases

  • Offline and cloud backends: use Kokoro locally or Noiz cloud for synthesis.
  • Timeline and simple modes: generate plain audio or per-segment, timeline-aligned narration.
  • Voice control: adjust voice, speed, emotion, and optional reference audio for cloning.
  • Use Case: create podcast narration, read articles aloud, or dub videos with synchronized timing.

Quick Start

Provide your text to the skill and specify an output file to generate speech using either the local Kokoro backend or the Noiz cloud service.

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 using local or cloud backends?

You can convert text to speech by submitting text to either the local Kokoro backend or the Noiz cloud service, specifying voice, speed, emotion, language, and output format to generate natural-sounding audio.

What do I need to generate timeline-aligned narration for scripts?

Timeline-aligned narration requires FFmpeg installed for timeline-mode processing, alongside your script text, to render per-segment audio timing for synchronized video dubbing or podcast generation.

Can I use voice cloning for text-to-speech synthesis?

Yes, voice cloning is supported by providing optional reference audio alongside your text, allowing the synthesis engine to replicate the voice characteristics for customized speech generation.

Do I need an API key to use the Noiz cloud text-to-speech backend?

Yes, using the Noiz cloud backend for text-to-speech synthesis requires an API key, whereas the Kokoro local backend requires installed tooling but operates offline without cloud credentials.

What is the best way to adjust speech emotion and speed for audio narration?

To adjust speech emotion and speed for audio narration, specify the desired voice, speed, emotion, and language parameters when submitting your text to the Kokoro or Noiz synthesis backend.