TTS

Convert text into natural-sounding speech using the z-ai-web-dev-sdk.

Updated Mar 29, 2026

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

Ready to run

npx skills add https://github.com/Mohabsmar/VoiceDev-2.0 --skill tts-mohabsmar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/Mohabsmar/VoiceDev-2.0/tree/main/skills/TTS
Command: npx skills add https://github.com/Mohabsmar/VoiceDev-2.0 --skill tts-mohabsmar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts plain text into natural-sounding speech to create voice-enabled applications, generate audio content, and improve accessibility.

Core Features & Use Cases

Text-to-speech conversion with multiple voices (tongtong, chuichui, xiaochen, jam, kazi, douji, luodo) and adjustable speed.
Output formats include WAV, MP3, and PCM, with optional streaming for PCM and backend-only usage.
CLI and SDK workflows, batch processing, dynamic content generation, and API route examples.
Important: z-ai-web-dev-sdk must be used on the server side.

Quick Start

Generate a WAV file from sample text using the tongtong voice to verify the TTS workflow.

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 for a web application backend?▼

To convert text to speech for a web application backend, use the z-ai-web-dev-sdk on the server side to synthesize natural speech. This approach enforces backend usage to securely generate audio files like WAV or MP3.

What audio formats and voices are available for text-to-speech generation?▼

Text-to-speech generation supports WAV, MP3, and PCM output formats with adjustable speed and volume. You can select from multiple natural-sounding voices including tongtong, chuichui, xiaochen, jam, kazi, douji, and luodo.

Can I use streaming audio for real-time voice synthesis?▼

Streaming audio for voice synthesis is supported exclusively for PCM format and requires backend-only usage. This allows continuous audio data delivery for real-time voice-enabled interfaces across web and mobile contexts.

What is the character limit for text-to-speech conversion?▼

The text-to-speech conversion enforces an input length limit of 1024 characters. This constraint ensures reliable processing when generating natural-sounding speech for chatbots, accessibility enhancements, and dynamic content.

How do I generate a WAV file from text using the z-ai-web-dev-sdk?▼

Generate a WAV file from text by calling the z-ai-web-dev-sdk on your server with the desired text string and specifying a voice like tongtong. This workflow handles the audio synthesis and outputs the completed WAV file.