zai-tts

SKILL.md

High-quality text-to-speech audio generation using GLM-TTS with customizable voices and playback parameters.

Converts text or file content to WAV audio via the uvx zai-tts command with configurable output paths

Supports three built-in system voices (Lila, Chloe, Ethan) plus custom cloned voices created on audio.z.ai

Adjustable speed (1.5x, etc.) and volume (2x, etc.) parameters for fine-tuned audio output

Requires environment variables ZAI_AUDIO_USERID and ZAI_AUDIO_TOKEN obtained from audio.z.ai console authentication

Zai-TTS

Generate high-quality text-to-speech audio using GLM-TTS service via the uvx zai-tts command.
Before using this skill, you need to configure the environment variables ZAI_AUDIO_USERID and ZAI_AUDIO_TOKEN,
which can be obtained by login audio.z.ai and executing localStorage['auth-storage'] in the console via F12 Developer Tools.

Usage

uvx zai-tts -t "{msg}" -o {tempdir}/{filename}.wav
uvx zai-tts -f path/to/file.txt -o {tempdir}/{filename}.wav

Changing speed, volume

uvx zai-tts -t "{msg}" -o {tempdir}/{filename}.wav --speed 1.5
uvx zai-tts -t "{msg}" -o {tempdir}/{filename}.wav --speed 1.5 --volume 2