Fast, private, local text-to-speech powered by Kokoro
Voice turns text, files, and standard input into natural Kokoro speech
entirely on your CPU. The model runs locally: text is not uploaded and no
account or network connection is required after installation.
Select from 54 voices across American and British English, Spanish, French,
Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese. Voice
can play speech immediately or write a 24 kHz WAV file for later use.
Command-line examples:
truevoice speak "Hello from Voice"
truevoice voices
truevoice speak --output speech.wav "Save this as a WAV file"
For the full Ubuntu GNOME Quick Settings experience, run this once after
installing the snap:
git clone --depth 1 https://github.com/t4ce/Voice.git
cd Voice
./tools/install_ubuntu_integration.sh
This host-side installer adds the Voice tile, language and voice selection,
Speak Clipboard, Speak Selection, and keyboard shortcuts for the current
user. The speech model remains local and only loads when Voice is switched on.