glow-speak is a fast, local, neural text to speech system that uses eSpeak-ng as a text/phoneme front-end.

git clone https://github.com/rhasspy/glow-speak.git
cd glow-speak/

python3 -m venv .venv
source .venv/bin/activate
pip3 install --upgrade pip
pip3 install --upgrade setuptools wheel
pip3 install -f 'https://synesthesiam.github.io/prebuilt-apps/' -r requirements.txt

python3 setup.py develop
glow-speak --version

The following languages/voices are supported:

• German
  • de_thorsten
• Chinese
  • cmn_jing_li
• Greek
  • el_rapunzelina
• English
  • en-us_ljspeech
  • en-us_mary_ann
• Spanish
  • es_tux
• Finnish
  • fi_harri_tapani_ylilammi
• French
  • fr_siwis
• Hungarian
  • hu_diana_majlinger
• Italian
  • it_riccardo_fasol
• Korean
  • ko_kss
• Dutch
  • nl_rdh
• Russian
  • ru_nikolaev
• Swedish
  • sv_talesyntese
• Swahili
  • sw_biblia_takatifu
• Vietnamese
  • vi_vais1000

glow-speak-download de_thorsten

glow-speak -v en-us_mary_ann 'This is a test.' --output-file test.wav

glow-speak-http-server --debug

Visit http://localhost:5002

Start the server:

glow-speak-socket-server --voice en-us_mary_ann --socket /tmp/glow-speak.sock

From a separate terminal:

echo 'This is a test.' | bin/glow-speak-socket-client --socket /tmp/glow-speak.sock | xargs aplay

Lines from client to server are synthesized, and the path to the WAV file is returned (usually in /tmp).