TTS

Convert text to speech in WAV, MP3, or PCM via the z-ai-web-dev-sdk.

Updated Jan 15, 2026

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

Ready to run

npx skills add https://github.com/Kin3Xc/promoly --skill tts-kin3xc

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: TTS
Source: https://github.com/Kin3Xc/promoly/tree/main/skills/TTS
Command: npx skills add https://github.com/Kin3Xc/promoly --skill tts-kin3xc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts text into natural-sounding speech for applications, enabling audio content generation, voice interfaces, and accessible narration.

Core Features & Use Cases

Voice variety: choose from multiple voices to fit the application tone.
Configurable speech: adjust speed and volume; supports WAV, MP3, and PCM formats.
Back-end integration: designed for server-side use with the z-ai-web-dev-sdk to power voice-enabled apps, chatbots, assistants, and IVR.

Quick Start

Use a quick example: z-ai tts -i "Hello, world!" -o ./output.wav

Frequently Asked Questions about TTS

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert text into natural speech for a backend application?▼

To convert text into natural speech for a backend application, use this skill with the z-ai-web-dev-sdk to generate audio files like WAV or MP3 server-side.

What audio formats and sample rates are supported for text-to-speech generation?▼

Text-to-speech generation supports WAV, MP3, and PCM output formats with a 24000 Hz sample rate, while streaming is restricted to PCM only.

Can I adjust voice speed and volume when generating speech with z-ai-web-dev-sdk?▼

Yes, you can adjust voice speed and volume when generating speech with z-ai-web-dev-sdk, and you can choose from multiple voices to fit your application tone.

What are the character limits for text-to-speech requests in backend services?▼

Text-to-speech requests in backend services enforce a strict 1024-character input limit per request to process audio generation effectively.

Does streaming text-to-speech work with MP3 or WAV formats?▼

Streaming text-to-speech does not work with MP3 or WAV formats; it is supported exclusively through PCM output at a 24000 Hz sample rate.