Installation requirements
Muyan-TTS needs to run under Linux environment, Ubuntu system is recommended. Main dependencies include Python 3.10, FFmpeg and other tools.
Installation steps
- Cloning GitHub repositories:
git clone https://github.com/MYZY-AI/Muyan-TTS.git - Create a conda virtual environment:
conda create -n muyan-tts python=3.10 -y - Install project dependencies:
make build - Download pre-trained model (requires about 20 GB of storage)
hardware requirement
- inference environment: NVIDIA A100 (40GB) or equivalent GPU recommended
- Training environment: Multi-card GPU clusters required for pre-training (total training cost ~$50,000)
- Memory Requirements: At least 16GB GPU video memory required for base model inference
Deployment Options
Supports local API deployment (default port 8020), which can be accessed via thepython api.pyLaunch services for easy integration into various applications.
This answer comes from the articleMuyan-TTS: Personalized Podcast Speech Training and SynthesisThe
May not be reproduced without permission:AI productivity tools " How to install and deploy Muyan-TTS and what hardware is required?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil