Skip to content
TakoAPI
Back to skills

zai-tts

by al-one

Git & GitHub
156Downloads reported by clawskills.sh
2Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text.

Description

What This Skill Does

Converts text or text files to speech audio using the GLM-TTS service via `uvx zai-tts`. Supports three built-in voices and custom cloned voices, with adjustable speed and volume. Output is saved as a WAV file.

Custom voice cloning support lets you use your own voice profiles, which most CLI TTS tools don't offer.

When to Use It

  • Listening to long articles during a commute
  • Converting meeting notes to audio for hands-free review
  • Reading code documentation aloud while away from the screen
  • Generating narration from written drafts for a podcast
  • Accessibility playback for users who prefer audio over reading

Example Workflow

INPUT

User asks: Read this paragraph aloud

AGENT
  1. 1

    Receives the text to convert

  2. 2

    Selects a voice (e.g., system_002 for Chloe)

  3. 3

    Runs uvx zai-tts -t "<text>" -o /tmp/output.wav --voice system_002

  4. 4

    Returns or plays the generated WAV file

OUTPUT

A WAV audio file containing the spoken text

Requirements

  • Account on audio.z.ai
  • ZAI_AUDIO_USERID: retrieved from audio.z.ai localStorage via browser DevTools console
  • ZAI_AUDIO_TOKEN: retrieved from audio.z.ai localStorage via browser DevTools console
  • uvx (uv toolchain): install via brew or pip

Installation

clawhub install al-one/zai-tts

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links