minimax-tts

Synthesize speech from text using the MiniMax Speech 2.8 API.

Updated Aug 23, 2026

Search Tags:#text-to-speech #audio #tts #speech synthesis #voice generation #minimax

Ready to run

npx skills add https://github.com/Ghostmonday/openclaw-custom-skills --skill minimax-tts-ghostmonday

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: minimax-tts
Source: https://github.com/Ghostmonday/openclaw-custom-skills/tree/main/minimax-speech
Command: npx skills add https://github.com/Ghostmonday/openclaw-custom-skills --skill minimax-tts-ghostmonday

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of generating speech from text using the MiniMax Speech 2.8 API, and allows for easy lookup of available voices.

Core Features & Use Cases

Text-to-Speech (TTS): Convert text into audio with precise control over voice, model, and audio settings.
Voice Catalog Lookup: Enumerate available system, cloned, or generated voices from MiniMax.
Use Case: Generate a professional-sounding voiceover for a marketing video using a specific MiniMax voice_id and high-fidelity audio settings.

Quick Start

Use the minimax-tts skill to convert the text "Hello, world!" into speech using the 'Sweet_Girl_2' voice and save it as an MP3 file.

Frequently Asked Questions about minimax-tts

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

FAQPage Schema

How do I generate speech from text using the MiniMax Speech 2.8 API?▼

To generate speech from text, you configure a request to the MiniMax Speech 2.8 API with your desired text, voice_id, and audio settings. This Skill automates that request process to synthesize and save the audio output.

Do I need a requests library and API key for text-to-speech voice generation?▼

Yes, text-to-speech voice generation requires the `requests` Python library to handle HTTP calls and a valid `MINIMAX_API_KEY` environment variable to authenticate with the MiniMax Speech 2.8 API.

How can I look up available voice models for MiniMax speech synthesis?▼

You can look up available voice models for MiniMax speech synthesis by using the Skill's voice catalog lookup feature. This enumerates all available system, cloned, and generated voices for your audio configurations.

Can I convert text to MP3 audio with a specific cloned voice?▼

Yes, you can convert text to MP3 audio using a specific cloned voice. By retrieving the cloned voice_id from the voice catalog lookup, you can target it in your MiniMax Speech 2.8 API request for precise audio generation.

What is the best way to automate voiceover generation for marketing videos?▼

Automating voiceover generation involves passing your marketing script text to the MiniMax Speech 2.8 API with a professional voice_id and high-fidelity audio settings. This Skill streamlines the synthesis process to produce the required audio file.

What are the limitations of using Python requests for MiniMax voice synthesis?▼

Using Python requests for MiniMax voice synthesis limits you to environments that support external HTTP calls and the `requests` library. You must also manage your `MINIMAX_API_KEY` securely and handle network responses manually.