https://github.com/logancyang/minimax-tts-skill
Agent Skill for minimax tts and voice cloning
https://github.com/logancyang/minimax-tts-skill
Last synced: about 2 months ago
JSON representation
Agent Skill for minimax tts and voice cloning
- Host: GitHub
- URL: https://github.com/logancyang/minimax-tts-skill
- Owner: logancyang
- Created: 2026-02-24T07:26:35.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-02-24T07:32:04.000Z (3 months ago)
- Last Synced: 2026-04-01T09:32:18.043Z (2 months ago)
- Language: Python
- Size: 5.86 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MiniMax TTS Skill
An agent skill for text-to-speech generation and voice cloning using the [MiniMax](https://www.minimaxi.com/) cloud API.
## Features
- **Text-to-Speech** — Generate speech from text with configurable voice, speed, pitch, and format
- **Voice Cloning** — Clone a voice from a reference audio file and use it for TTS
- No pip dependencies — uses only Python stdlib
## Setup
Set the following environment variables:
```bash
MINIMAX_API_KEY="your-api-key"
MINIMAX_GROUP_ID="your-group-id" # required for voice cloning
```
## Quick Start
```bash
# Generate speech
python scripts/tts.py tts --text "Hello world" --voice male-qn-qingse --output hello.mp3 --format mp3
# Clone a voice
python scripts/tts.py clone --audio reference.wav --voice-id my_voice --text "Test sentence"
```
See [SKILL.md](SKILL.md) for full usage details and available options.