The following environment requirements need to be met before deployment:
- operating system: Windows 10/11 (64-bit) or Linux (Debian/Ubuntu recommended)
- Python: 3.10 or higher
- essential component:: Git (for code cloning), eSpeak NG (text-phonization processing)
- GPU acceleration optional: Requires NVIDIA graphics and CUDA support, Linux requires additional installation of libsndfile1 and ffmpeg.
Special note: Windows users need to reboot the terminal after installing eSpeak NG. sudo apt install espeak-ng
(Linux) or install the .msi package (Windows) to complete the dependency installation.
This answer comes from the articleKitten-TTS-Server: a self-deployable lightweight text-to-speech serviceThe