TTS

Convert text to speech audio with speed, volume, and format controls.

Updated Jan 29, 2026

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

Ready to run

npx skills add https://github.com/TIAN0517/iosboss --skill tts-tian0517

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/TIAN0517/iosboss/tree/main/temp_extract/99999999/skills/TTS
Command: npx skills add https://github.com/TIAN0517/iosboss --skill tts-tian0517

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The TTS skill enables programs and services to generate natural-sounding speech from text, providing accessible, engaging audio output for apps, assistants, and content.

Core Features & Use Cases

Voice variety: supports multiple voices to convey tone and language.
Control & formats: adjustable speed and volume; outputs in WAV, MP3, or PCM for backend audio generation.
Real-world use cases: build narration for articles, dynamic audio responses for chatbots, and accessible content for users with hearing or reading challenges.

Quick Start

Use the TTS skill with the z-ai-web-dev-sdk in backend code to convert text to speech, for example by running the provided scripts/tts.ts on a server to generate an audio file from your text.

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 audio on a backend server?▼

To convert text to speech on a backend, use the z-ai-web-dev-sdk to run server-side scripts that process your input text and generate natural-sounding speech audio files. This approach supports dynamic audio generation for applications like chatbots and content narration.

What audio output formats are supported for text-to-speech generation?▼

Text-to-speech generation supports WAV, MP3, and PCM audio output formats. These options allow you to integrate generated speech audio into various backend systems, content creation workflows, and accessibility tools based on your specific format requirements.

Can I control the speed and volume of generated speech audio?▼

Yes, you can control both the speed and volume of generated speech audio. The text-to-speech process also supports multiple voices, allowing you to adjust tone and language to create natural-sounding narration for articles or dynamic chatbot responses.

What is the maximum character limit for text-to-speech input processing?▼

The maximum character limit for text-to-speech input processing is 1024 characters. Enforcing this input limit ensures reliable audio generation and stable streaming performance when converting your text into natural-sounding speech on the server.

Does the z-ai-web-dev-sdk support streaming text-to-speech audio?▼

Yes, the z-ai-web-dev-sdk supports optional streaming for text-to-speech audio generation on the server. Streaming enables real-time audio delivery for chat assistants and accessibility tools, reducing wait times for longer text inputs within the character limit.