TTS

Convert text into spoken audio using the z-ai-web-dev-sdk backend.

Updated Dec 26, 2025
One-click install
npx skills add https://github.com/yutaoshao/agent-skills --skill tts-yutaoshao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/yutaoshao/agent-skills/tree/main/glm-skills/TTS
Command: npx skills add https://github.com/yutaoshao/agent-skills --skill tts-yutaoshao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk.

What problem does it solve?

This solution converts text into spoken audio to automate narration, accessibility, and voice-enabled features, saving time and ensuring consistent voice output.

Core Features & Use Cases

  • Multiple voices and adjustable speed and volume for personalized speech.
  • Output formats including wav, mp3, and pcm for broad compatibility.
  • Backend-only usage with examples for dynamic content generation, app integration, and accessibility.

Quick Start

Provide the input text and optional voice, speed, and format to generate an audio file.

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 in a backend application?

To convert text to speech in a backend application, you can use an SDK that processes text inputs and generates audio files. This approach automates narration and supports dynamic content generation without browser dependency.

What audio formats can I generate from text using a TTS SDK?

You can generate wav, mp3, and pcm audio formats from text using a TTS SDK. These output formats ensure broad compatibility for various playback environments and content delivery networks.

Can I adjust voice speed and volume when generating speech from text?

Yes, you can adjust voice speed and volume when generating speech from text. The SDK supports multiple voices and configurable parameters to create personalized audio output for accessibility features.

What is the maximum character limit for text-to-speech conversion?

The maximum character limit for text-to-speech conversion is 1024 characters per input. Enforcing this input limit ensures robust error handling and stable streaming considerations for production deployments.

Does text-to-speech SDK work for accessibility and content narration?

Yes, text-to-speech SDK works for accessibility and content narration by converting written text into natural spoken audio. This enables voice-enabled features and automated narration for dynamic backend content.