skills.rest
storyclaw-official
storyclaw-officialOFFICIAL
Explore all skills by this author →
Website𝕏@storyclawaiGitHub

minimax-tts

Convert Chinese Mandarin text to ogg/opus speech via MiniMax T2A v2 API.

Updated Feb 11, 2026
Search Tags:#text-to-speech#chinese#audio generation#tts#minimax#mandarin
One-click install
npx skills add https://github.com/storyclaw-official/storyclaw-assistant --skill minimax-tts
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: minimax-tts
Source: https://github.com/storyclaw-official/storyclaw-assistant/tree/main/skills/minimax-tts
Command: npx skills add https://github.com/storyclaw-official/storyclaw-assistant --skill minimax-tts

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill converts Chinese Mandarin text into natural-sounding speech using the MiniMax T2A v2 API, optimizing for clarity and low latency in conversational AI scenarios.

Core Features & Use Cases

  • High-Quality Chinese TTS: Generates natural and fluent Mandarin speech.
  • Multiple Voice Options: Supports various female voices optimized for different tones and use cases.
  • Ogg/Opus Output: Delivers audio in a widely compatible format, suitable for real-time applications.
  • Use Case: Enable your AI assistant to deliver morning greetings, weekly summaries, or respond to user queries with a natural voice, enhancing user engagement.

Quick Start

Use the minimax-tts skill to speak the text "你好，世界！" with the default voice.

Frequently Asked Questions about minimax-tts

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

FAQPage Schema
How do I convert Chinese Mandarin text to speech for an AI assistant?▼

You can convert Chinese Mandarin text to speech using the MiniMax T2A v2 API, which generates natural-sounding audio. This approach provides low latency and high-quality output suitable for conversational AI scenarios.

What audio format does MiniMax text-to-speech output for real-time applications?▼

MiniMax text-to-speech outputs audio in the ogg/opus format. This widely compatible format is specifically chosen because it is well-suited for real-time applications and low-latency conversational delivery.

Do I need ffmpeg to generate Mandarin speech with the MiniMax T2A v2 API?▼

Yes, you need ffmpeg installed because it is required for audio transcoding when generating Mandarin speech. You also need to configure valid API keys and group IDs to authenticate your requests to the service.

Can I use different voices for Chinese text-to-speech generation?▼

Yes, you can use different voices for Chinese text-to-speech generation. The MiniMax T2A v2 API supports various voice options, including multiple female voices that are specifically optimized for different tones and use cases.

What is the best way to deliver morning greetings using Chinese TTS?▼

The best way to deliver morning greetings using Chinese TTS is to leverage the MiniMax T2A v2 API for low-latency, natural-sounding Mandarin speech. This enhances user engagement by providing fluent, conversational voice responses.

Related Skills

Explore More Content & Communication Skills→
lxh755818-botlxh755818-bot

minimax-tts

Convert text to speech via MiniMax API and send OGG audio to Feishu.

Community
Intermediate
rovannirovanni
1

telegram-voice

Transcribe Telegram audio messages with Whisper and reply via local TTS.

Community
Advanced
rgbkrkrgbkrk
20

voice

Transcribe speech and synthesize text with Rust and candle.

Community
Advanced
akrindevakrindev
4

gemini-tts

Generates speech from text using Google Gemini TTS models via Python scripts.

Community
Intermediate