larynx 1.1.0

Larynx is a speech synthesis system that focuses on providing lightweight and privacy-focused text-to-speech (TTS) capabilities. Larynx is built with the aim of offering an offline TTS solution, meaning it does not require an internet connection for speech synthesis.

The project utilizes the Tacotron 2 and WaveGlow models, which are well-known neural network architectures for generating human-like speech from text. Larynx provides pre-trained models for different languages, enabling users to convert text into speech in their preferred language.

Larynx offers a straightforward API and command-line interface (CLI) for integrating the TTS functionality into various applications. It allows developers to generate high-quality speech from text strings programmatically, enabling applications to provide natural and intelligible audio output.

Stars: 823, Watchers: 823, Forks: 49, Open Issues: 42

The rhasspy/larynx repo was created 3 years ago and the last code push was 9 months ago.
The project is popular with 823 github stars!

How to Install larynx

You can install larynx using pip

pip install larynx

or add it to a project with poetry

poetry add larynx

Package Details

Author

Michael Hansen

License

Homepage

https://github.com/rhasspy/larynx

PyPi:

https://pypi.org/project/larynx/

GitHub Repo:

https://github.com/rhasspy/larynx

Classifiers

Related Packages

Errors

A list of common larynx errors.

Code Examples

Here are some larynx code examples and snippets.

GitHub Issues

The larynx package has 42 open issues on GitHub

• Jinga2 requirement fix
• Fix download folder not found during docker install
• larynx.text_to_speech() function doesn't work
• Voice suggestion: GLaDOS from portal

See more issues on GitHub