Machine learning text-to-speech for your terminal. Hear text read aloud by realistic voices, from a file or your clipboard.
.gitignore | ||
env.sh | ||
main.py | ||
README.md | ||
requirements.txt |
Simple TTTS
A simple text to speech powered by kokoro.
Setup
Create new environment. Here I use conda
$ conda create -n tts
Because I use an intel-based laptop, I use ipex-llm environment with pytorch 2.6
### for Intel XPU specific device usage:
$ conda create -n tts --clone llm-pt26
Activate the environment and install the dependencies
$ conda activate tts
$ python -m pip install -r requirements.txt
Because vlc
to automatically play the generated audio, you will have to install it:
sudo apt update
sudo apt install vlc
Note: installing vlc
via flatpak or snap will not work, as the code need access to libvlc
.