Skip to content
TakoAPI
Back to skills

mm-easy-voice

by blue-coconut

Media & Streaming
291Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Simple text-to-speech skill using MiniMax Voice API.

Description

What This Skill Does

MiniMax Easy Voice converts text to speech using the MiniMax Voice API. It supports selecting from a catalog of system voices, cloning voices from audio samples, and designing custom voices from text descriptions. Inline pause markup lets you control timing within generated audio.

Voice cloning and inline pause control give more flexibility than basic TTS APIs that only offer fixed system voices.

When to Use It

  • Generating voiceover audio for explainer videos
  • Converting written articles to audio for on-the-go listening
  • Prototyping podcast episodes from written scripts
  • Creating narration for multilingual content in English and Chinese
  • Building custom voice personas for chatbot interfaces

Example Workflow

INPUT

User asks: Convert this paragraph to speech using a female voice and save it as output.mp3

AGENT
  1. 1

    Verify MINIMAX_VOICE_API_KEY is set in the environment

  2. 2

    Run list-voices to identify a suitable female voice ID

  3. 3

    Call mmvoice.py tts with the paragraph text, selected voice ID, and output path

  4. 4

    Return the generated output.mp3 file to the user

OUTPUT

An MP3 audio file with the paragraph spoken in the selected female voice

Requirements

  • MiniMax Voice API key set as the MINIMAX_VOICE_API_KEY environment variable, obtained from the MiniMax platform

Installation

clawhub install blue-coconut/mm-easy-voice

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

Links