AI Skill Market Insights

Real data. Real impact.

Popularity

Rising

Emerging

Active Users

0+

Developers

Time Saved

2+ hrs

Per week

Source

GitHub

Open source

Be Part of the 0+ Developer Community

Skills give you superpowers. Install in 30 seconds.

GLM-TTS brings high-quality text-to-speech generation into your agent workflow using the GLM-TTS service. It converts text into natural-sounding audio with three built-in voices, adjustable speed and volume, and support for custom voice cloning — enabling agents to produce spoken content for accessibility, presentations, podcasts, or any audio output need.

Key Features

Three built-in voices — Lila (cheerful female), Chloe (elegant female), and Ethan (sunny male) — covering common tone and style needs
Adjustable audio parameters including speed and volume controls for fine-tuning output to match the intended use case
Custom voice cloning support via audio.z.ai, enabling brands or individuals to use their own pre-cloned voice profiles
Flexible text input accepting direct text strings or file paths for processing longer content
WAV output format saved to the local filesystem for immediate playback or further processing

Use Cases

Generating audio versions of written content for accessibility compliance or user preference
Creating voiceovers for presentations, demos, or tutorial videos without recording equipment
Building audio content pipelines that convert blog posts, documentation, or reports into listenable format
Prototyping podcast or narration content with different voice options before committing to professional recording

How It Works

The skill uses the

uvx zai-tts

CLI tool to interface with the GLM-TTS service. Users provide text content (directly or from a file), select a voice profile, and optionally adjust speed and volume parameters. The service processes the text and returns a WAV audio file saved to the local filesystem. Authentication requires two credentials — a user ID and token — extracted from the audio.z.ai browser interface.

Getting Started

Install the

uv

package manager via Homebrew or pip to access the

uvx

binary. Configure two environment variables —

ZAI_AUDIO_USERID

and

ZAI_AUDIO_TOKEN

— obtained from the browser developer console at audio.z.ai. Then run

uvx zai-tts --text "Your text here" --voice lila

to generate your first audio file.

License

MIT-0 (Free to use, modify, and redistribute. No a

🗣️ Text-to-speech using GLM-TTS for generating audio

AI Skill Market Insights

Be Part of the 0+ Developer Community

Key Features

Use Cases

How It Works

Getting Started

License

Quick Start

Manual Installation

TEAR & SHARE

Tags

using-git-worktrees

using-superpowers

🎤 Transcribe audio files using Qwen ASR. STT

Audio Handler

Audio Script Writer

Channels

Learn

Compare

Company