Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Free ready-to-run AI notebooks for Text-to-Video, Image-to-Video, Voice Cloning, TTS & AI Music. Run on Kaggle, Colab, HuggingFace Spaces, Paperspace & Vast.ai — zero setup, one-click launch.
A Gradio-based web UI for voice cloning and voice design, powered by Qwen3-TTS & VibeVoice. Can use Whisper or VibeVoice-ASR for automatic transcription.