TTS

Name: TTS
Availability: InStock
Author: chancoute

Convert text into speech with the z-ai-web-dev-sdk for backend audio generation.

Updated Jan 8, 2026

Search Tags:#backend #text-to-speech #tts #audio-generation #voices #z-ai-web-dev-sdk

Ready to run

npx skills add https://github.com/chancoute/sgin --skill tts-chancoute

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/chancoute/sgin/tree/main/skills/TTS
Command: npx skills add https://github.com/chancoute/sgin --skill tts-chancoute

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables developers to transform written text into natural-sounding speech using the z-ai-web-dev-sdk, supporting multiple voices, speeds, and output formats for backend applications.

Core Features & Use Cases

Voice variety: Choose among multiple voices to suit tone and language.
Configurable speech: Adjust speed and volume for precise narration.
Backend-ready: Designed for server-side generation in API routes or services.

Quick Start

Use the tts.ts script to generate a sample WAV from "Hello, world!" in your Skill Location.

Frequently Asked Questions about TTS

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

FAQPage Schema

How do I generate speech from text in a backend application?▼

To generate speech in a backend application, you can use the z-ai-web-dev-sdk to convert text into natural-sounding audio. It is designed for server-side generation in API routes or services, supporting multiple voices and output formats for safe, scalable operations.

Can I adjust the speed and volume for text-to-speech generation?▼

Yes, you can configure both speed and volume for text-to-speech generation to achieve precise narration. The Skill enforces specific constraints on these parameters alongside input limits to ensure safe and scalable audio generation.

What is the best way to implement voice variety for accessibility features?▼

The best way to implement voice variety for accessibility is using a backend text-to-speech solution that offers multiple voices. This Skill allows you to choose among various voices to suit different tones and languages for accessibility needs.

Does the z-ai-web-dev-sdk support generating WAV files for narration?▼

Yes, the z-ai-web-dev-sdk supports generating WAV files for narration. You can use the provided tts.ts script to generate a sample WAV file directly from your text input in your Skill Location.

Are there input limits for backend text-to-speech conversion?▼

Yes, there are enforced input limits for backend text-to-speech conversion. The Skill enforces these constraints along with voice options, speed, and volume limitations to ensure safe and scalable TTS operations.