TTS

Convert text to speech with the z-ai-web-dev-sdk on Node.js backends.

Updated Jan 22, 2026
One-click install
npx skills add https://github.com/zakarooo/dataup --skill tts-zakarooo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/zakarooo/dataup/tree/main/TTS
Command: npx skills add https://github.com/zakarooo/dataup --skill tts-zakarooo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) components.

What problem does it solve?

This Skill enables backend applications to convert text into natural-sounding speech using the z-ai-web-dev-sdk, enabling accessible content creation and dynamic audio generation.

Core Features & Use Cases

  • Text-to-speech generation with multiple voices and adjustable speed and output formats.
  • Suitable for accessibility tools, voice-enabled apps, e-learning narration, and media content production.
  • Example task: generate a narration audio file from article text for a podcast or online course.

Quick Start

Install the SDK in your backend project, create a ZAI instance, call zai.audio.tts.create with input text, then save the resulting audio buffer to a file (e.g., output.wav). See the tts.ts sample script in the skill's scripts directory for a ready-to-run example.

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?

Text-to-speech conversion in Node.js uses the z-ai-web-dev-sdk. Install the SDK, create a ZAI instance, call zai.audio.tts.create with your input text, then extract the audio buffer from the Response object and save it to a file like output.wav or output.mp3.

What audio formats does TTS support?

TTS supports wav, mp3, and pcm output formats. You specify the desired format when calling the zai.audio.tts.create method, and the resulting audio buffer can be written to a file in your chosen format.

Can I adjust voice speed and select different voices?

Yes, TTS supports multiple voices and adjustable speed parameters. Pass these options when creating your text-to-speech request through the z-ai-web-dev-sdk to customize the output voice and narration pace.

What are common use cases for backend text-to-speech?

Backend TTS enables accessibility tools, voice-enabled applications, e-learning narration, and media content generation. Common examples include generating podcast audio from article text, creating audiobook narration, and producing dynamic voiceovers for online courses.

Do I need specific dependencies to use TTS?

Yes, you must install the z-ai-web-dev-sdk in your Node.js backend project. This is the only required dependency for text-to-speech functionality.