mm-voice-maker

Automate voice synthesis, cloning, and FFmpeg audio post-processing via MiniMax Voice API.

2|Updated Apr 6, 2026

Search Tags:#automation #ffmpeg #audio processing #tts #voice cloning #voice design #segment-based

Ready to run

npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill mm-voice-maker

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mm-voice-maker
Source: https://github.com/augustscl/awesome-xiawang-skills/tree/main/mm-voice-maker
Command: npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill mm-voice-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, websockets, ffmpeg-python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Automates voice synthesis, voice cloning, voice design, and audio post-processing to streamline multimedia voice workflows.

Core Features & Use Cases

Synchronous and asynchronous TTS (single-voice or multi-segment) powered by MiniMax Voice API
Voice cloning and voice design to create custom voices for branding, narration, and characters
Segment-based TTS with per-segment voices and emotions for complex narratives
FFmpeg-based audio processing: convert, merge, normalize, trim, and remove silence for polished outputs
CLI-driven workflow coverage including environment checks, voice management, and robust error handling

Quick Start

Provide a quick example by synthesizing a short text with a chosen voice and saving it as an MP3.

Frequently Asked Questions about mm-voice-maker

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

FAQPage Schema

How do I automate multi-voice TTS and audio post-processing for video narration?▼

You can automate multi-voice TTS and audio post-processing by using segment-based voice synthesis with the MiniMax Voice API, then applying FFmpeg operations to merge, normalize, and trim the resulting audio clips.

Can I clone a custom voice and assign different emotions to audio segments?▼

Yes, custom voice cloning and design are supported alongside segment-based TTS, enabling you to assign distinct voices and emotions to individual narrative segments for complex audio productions.

How do I remove silence from audio files using FFmpeg automation?▼

Remove silence from audio files through automated FFmpeg-based audio processing, which handles silence removal alongside conversion, merging, normalization, and trimming for polished multimedia outputs.

Does this voice synthesis workflow require a specific API or environment setup?▼

The workflow requires setting up the MiniMax Voice API integration and running environment checks, utilizing Python dependencies like requests, websockets, and ffmpeg-python to manage synchronous and asynchronous TTS operations.

What is the best way to manage and merge multiple AI-generated voice clips?▼

The best way to manage and merge AI-generated voice clips is using a CLI-driven workflow that handles voice management and applies FFmpeg-based audio merging to combine individual TTS segments into a single output.

Are there limitations when using asynchronous TTS for complex audio narratives?▼

While asynchronous TTS supports complex segment-based narratives with per-segment voices, limitations may arise from API rate limits or audio synchronization issues that require robust error handling during the merging process.