The following environment needs to be prepared before deployment:
- basic system: Windows 10/11 (64-bit) or Linux (Debian/Ubuntu recommended)
- Python environment: Version 3.10 and above
- Required Components: Git code management tool and eSpeak NG phoneme engine
- GPU acceleration (optional): NVIDIA graphics card required and CUDA driver installed
Special attention:
- Windows users need to install espeak-ng-X.XX-x64.msi after theRestart the terminal
- Linux users need to execute the
sudo apt install espeak-ng libsndfile1 ffmpegInstallation of dependencies - GPU users need to additionally configure NVIDIA Container Toolkit (for Docker deployment)
This answer comes from the articleKitten-TTS-Server: a self-deployable lightweight text-to-speech serviceThe
May not be reproduced without permission:AI productivity tools " What pre-requisite environment preparation is needed to deploy Kitten-TTS-Server?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil