TTS by Mozilla

Using open source code

Direct Installation

TTS supports python >= 3.6, <3.9.

If you are only interested in synthesizing speech with the released TTS models, installing from PyPI is the easiest option.

pip install TTS

If you plan to code or train models, clone TTS and install it locally.

git clone
pip install -e .

Custom installation

However, the version is lower in github than in Pypl, losing many models and features. Therefore, we need to download the package from Pypl, extract manually to local path, and install using extracted files so that modified code will be carried later.

Pip download without installation

Create a new requirement.exe file, fill in all packages that needs to be downloaded: tts

in the same dir, use command pip download -d <dir to save downloaded files> -r requirement.txt


extract TTS-0.5.0.tar.gz, use command pip install -e . in the extracted dir to install TTS.

Config TTS

  • change max_decoder_steps in .\tts\configs\

Install on Raspi



repo link


  • conda create -n tts python=3.7.10
  • conda activate tts
  • cd <path to install>
  • git clone …