TTS

Convert text to speech audio via the z-ai-web-dev-sdk backend.

2.7k|627|Updated Sep 11, 2025
One-click install
npx skills add https://github.com/jjyaoao/HelloAgents --skill tts-jjyaoao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/jjyaoao/HelloAgents/tree/main/skills/TTS
Command: npx skills add https://github.com/jjyaoao/HelloAgents --skill tts-jjyaoao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables developers to convert written content into natural-sounding speech, reducing the manual burden of recording or synthesizing audio.

Core Features & Use Cases

  • Multiple voices supported for diverse narration.
  • Adjustable speed and volume controls to fine-tune tone and emphasis.
  • Output formats include WAV, MP3, and PCM with backend integration via z-ai-web-dev-sdk.
  • Use cases include accessibility, narration, voice-enabled assistants, and dynamic content generation.

Quick Start

Provide input text and call the TTS function to generate and save 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 audio using backend z-ai-web-dev-sdk?

To convert text to speech, call the TTS function with your input text to generate and save an audio file via the z-ai-web-dev-sdk backend, which handles synthesizing natural speech from written content.

What audio formats and sample rate does text-to-speech generation support?

Text-to-speech generation supports output formats including WAV, MP3, and PCM, operating at a 24000 Hz sample rate to ensure high-quality natural speech audio playback.

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

Yes, generating speech from text supports adjustable speed controls from 0.5 to 2.0 and volume controls greater than 0 up to 10, allowing fine-tuning of tone and emphasis for multiple voices.

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

Text-to-speech conversion enforces a maximum input limit of 1024 characters per request, requiring the backend to return an ArrayBuffer via response.arrayBuffer() to handle the generated audio data.

When do I need to use text-to-speech audio for accessibility or narration?

You need text-to-speech audio for accessibility when providing dynamic content generation or voice-enabled assistant applications, reducing the manual burden of recording or synthesizing audio for narration.

Does text-to-speech conversion work with multiple voices for diverse narration?

Text-to-speech conversion supports multiple voices for diverse narration, enabling developers to generate natural-sounding speech tailored to specific content types and accessibility requirements.