TTS

Convert text into speech audio in wav, mp3, and pcm formats.

Updated Feb 7, 2026

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

Ready to run

npx skills add https://github.com/jitenkr2030/AutoReel-AI --skill tts-jitenkr2030

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/jitenkr2030/AutoReel-AI/tree/main/skills/TTS
Command: npx skills add https://github.com/jitenkr2030/AutoReel-AI --skill tts-jitenkr2030

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

TTS converts text into natural-sounding speech, enabling automated narration, voice-enabled applications, and accessible content generation.

Core Features & Use Cases

Multiple voices: Select from a range of voices to fit tone and audience.
Speed control & formats: Adjust speaking rate and output formats (wav, mp3, pcm).
Backend-only operation: Use z-ai-web-dev-sdk in server-side code to generate audio for apps, tutorials, e-learning, IVR, and accessibility features.

Quick Start

Generate speech from text by creating a TTS instance, calling the SDK with your input, and saving the audio to a file. For example, produce a WAV narration for an onboarding tutorial by converting a paragraph of text into audio.

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?▼

You can convert text to speech audio on a backend server using this Skill with the z-ai-web-dev-sdk, which processes input text up to 1024 characters into natural-sounding speech.

What audio formats can I generate for text-to-speech narration?▼

You can generate speech audio in wav, mp3, and pcm formats, allowing flexible integration into various voice-enabled applications, IVR systems, and accessibility tools.

Does this text-to-speech Skill work in a browser environment?▼

No, this text-to-speech Skill requires a backend environment to operate, using the z-ai-web-dev-sdk within server-side code to generate and save audio files.

Can I adjust the speaking speed and select different voices for speech synthesis?▼

Yes, you can adjust the speaking rate and select from multiple voices to fit your audience and tone when synthesizing speech from text.

What is the maximum character limit for text input when generating speech?▼

The maximum input length for generating speech is 1024 characters per request, which is suitable for short narrations like onboarding tutorials or e-learning modules.