minimax-tts

Name: minimax-tts
Availability: InStock
Author: lxh755818-bot

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

Updated Apr 30, 2026

Search Tags:#API #text-to-speech #MiniMax API #Feishu integration #audio messaging

Ready to run

npx skills add https://github.com/lxh755818-bot/obsidian-vault --skill minimax-tts-lxh755818-bot

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: minimax-tts
Source: https://github.com/lxh755818-bot/obsidian-vault/tree/main/backup/skills/media/minimax-tts
Command: npx skills add https://github.com/lxh755818-bot/obsidian-vault --skill minimax-tts-lxh755818-bot

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the process of converting text to speech and sending the generated audio to Feishu, providing a convenient way to create and share spoken messages.

Core Features & Use Cases

Text-to-Speech Conversion: Utilizes the MiniMax API to convert text to high-quality speech using various voice options.
Audio Formatting: Converts the generated speech to OGG/opus format, ensuring compatibility with Feishu.
Feishu Integration: Send the audio message to a specified chat within Feishu, complete with duration information.
Use Case: Easily create and share voice messages within team communications on Feishu without the need for external software.

Quick Start

Convert the text "Hello, this is a test message." to speech and send it to the chat "oc_2e5cc02fdda5aef65a7f9ca03127eda5".

Frequently Asked Questions about minimax-tts

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

FAQPage Schema

How do I convert text to speech and send it as an audio message to Feishu?▼

To convert text to speech and send it to Feishu, this Skill uses the MiniMax API v2 to generate audio, formats it into OGG/opus, and sends it directly to a specified Feishu chat with duration tracking.

Do I need ffmpeg to send MiniMax text-to-speech audio to a Feishu chat?▼

Yes, you need ffmpeg installed to process text-to-speech audio for Feishu. It handles the required audio formatting and conversion to OGG/opus format, ensuring the generated speech is compatible with Feishu messaging.

What API credentials are required for MiniMax text-to-speech and Feishu integration?▼

MiniMax text-to-speech and Feishu integration require a MINIMAX_CN_API_KEY for audio generation and Feishu app credentials for messaging. You must configure these environment variables before executing the text-to-speech workflow.

How does audio formatting work when sending MiniMax API speech to Feishu?▼

Audio formatting for Feishu involves converting the MiniMax API speech output into OGG/opus format. This encoding ensures the audio message meets Feishu's compatibility requirements and includes accurate duration metadata for playback.

Can I use the MiniMax API to create voice messages for team communication in Feishu?▼

Yes, you can use the MiniMax API to create voice messages for Feishu team communication. It converts text into high-quality speech using various voice options and sends the audio directly to specified chats without external software.

What are the limitations of using MiniMax API for text-to-speech in Feishu?▼

Limitations of using MiniMax API for text-to-speech in Feishu include strict dependencies on ffmpeg for audio formatting and specific environment variables like MINIMAX_CN_API_KEY. Without these, the OGG/opus audio conversion and chat delivery will fail.