skills.rest
tony2015116
tony2015116COMMUNITY
Explore all skills by this author →
Website𝕏@tonyituiteGitHub

mm-voice-maker

Synthesize and clone voices with MiniMax Voice API and FFmpeg.

Updated Feb 26, 2026
Search Tags:#text-to-speech#FFmpeg#audio processing#voice cloning#MiniMax Voice API
One-click install
npx skills add https://github.com/tony2015116/openclaw-backup --skill mm-voice-maker-tony2015116
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mm-voice-maker
Source: https://github.com/tony2015116/openclaw-backup/tree/main/skills/mm-voice-maker
Command: npx skills add https://github.com/tony2015116/openclaw-backup --skill mm-voice-maker-tony2015116

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables users to easily create custom voices, synthesize speech, and process audio files using the MiniMax Voice API and FFmpeg, reducing the time and effort required for voice synthesis and audio manipulation.

Core Features & Use Cases

  • Custom Voice Creation: Design and clone custom voices from audio samples.
  • Text-to-Speech (TTS): Convert text to speech with various models and emotions.
  • Audio Processing: Convert, merge, normalize, and trim audio files.
  • Use Case: Imagine you need a custom voice for a podcast or a professional presentation. Use this Skill to design a voice, synthesize speech from text, and process the audio files to achieve the desired sound quality.

Quick Start

Generate a speech file from the text "Hello, world!" using the voice "female-shaonv" and save it as "hello.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 clone a custom voice from an audio sample for text-to-speech?▼

To clone a custom voice, you provide an audio sample to the MiniMax Voice API, which generates a custom voice model for synthesizing speech from your text inputs.

Can I add emotion detection when converting text to speech?▼

Yes, text-to-speech synthesis supports emotion detection. This feature analyzes input text to apply appropriate emotional tones, generating expressive and natural-sounding speech outputs.

What audio processing operations does FFmpeg support for post-processing TTS files?▼

FFmpeg enables audio processing operations including converting, merging, normalizing, and trimming audio files, allowing you to refine and adjust the final sound quality of synthesized speech outputs.

Do I need to install websockets and requests to use MiniMax Voice API for voice synthesis?▼

Yes, utilizing the MiniMax Voice API for voice synthesis requires the requests and websockets dependencies to handle the network communication needed for sending text and receiving generated audio.

What is the best way to create a professional podcast voice from text?▼

The best way to create a podcast voice is using text-to-speech synthesis to generate speech, followed by audio processing to normalize and merge the audio files for high-quality sound output.

Related Skills

Explore More Content & Communication Skills→
hoanghd218hoanghd218
3

mkt-vbee-tts-to-mp3

Convert Vietnamese and English text into MP3 voiceovers via the VBee API.

Community
Intermediate
CoachSteffCoachSteff
1

videoeditor

Automates video editing tasks such as trimming, merging, and formatting with FFmpeg and NLP.

Community
Advanced
augustsclaugustscl
2

mm-voice-maker

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

Community
Advanced
softweeksoftweek

openai-whisper

Transcribe and translate local audio files using the Whisper CLI.

Community
Intermediate