TTS

Convert text into speech with configurable voices, speed, and formats.

26|15|Updated Dec 25, 2025

Search Tags:#backend #text-to-speech #nodejs #audio-generation #z-ai-web-dev-sdk #voice-synthesis

Ready to run

npx skills add https://github.com/AnswerZhao/agent-skills --skill tts-answerzhao

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables scalable, backend-driven conversion of text into natural-sounding speech, empowering apps to deliver audio content and accessibility features without client-side processing.

Core Features & Use Cases

Voice customization: Select from multiple voices, adjust speed and output format (wav, mp3, pcm) for books, tutorials, IVR prompts, and more.
Backend-first workflow: Generate audio entirely on the server using z-ai-web-dev-sdk, enabling safe handling of keys and data.
Use cases: Create narrated content for e-learning, chatbots, announcements, and assistive technologies in apps.

Quick Start

Install the z-ai-web-dev-sdk, create a Node.js script that calls zai.audio.tts.create with your text, and save the resulting audio buffer to a file. Then run the script with node.

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 Node.js backend?▼

To convert text to speech in a Node.js backend, install the z-ai-web-dev-sdk, call zai.audio.tts.create with your text, and save the resulting audio buffer to a file.

Can I generate audio in different formats like wav or mp3?▼

Yes, you can generate audio in different formats including wav, mp3, and pcm when using the voice synthesis parameters available in the z-ai-web-dev-sdk.

Does server-side text-to-speech generation support multiple voices?▼

Yes, server-side text-to-speech generation supports multiple voices and allows you to adjust the speed and output format for your specific audio content requirements.

What is the best way to handle API keys for voice synthesis in web applications?▼

The best way to handle API keys for voice synthesis is executing text-to-speech generation entirely on the server side using a Node.js backend, which ensures safe key and data handling.

How does backend-driven audio generation help with app accessibility?▼

Backend-driven audio generation helps with app accessibility by converting text into natural-sounding speech on the server, allowing apps to deliver audio content without client-side processing.

Are there limitations to using client-side processing for text-to-speech?▼

Client-side processing for text-to-speech can expose API keys and limit scalable audio generation, which is why this skill uses a backend-first workflow to ensure safe server-side execution.