Articulatory (text-to-) speech synthesis for Python
Project description
This Python library provides an implementation of the articulatory synthesizer VocalTractLab.
Core features are:- a one dimensional aero-acoustic simulation of vocal tract dynamics using a vocal tract model based on MRI scans of a human vocal tract- synthesis of artificial speech through high-level gestural control or low- level motor control of individual articulators through dynamic targets- extensive visualization options- estimation of articulatory targets from audio files directly (pitch target- estimation) or from arbitrary data (e.g. articulatory measurements)- phoneme-to-speech functionality and a basic text-to-speech pipeline- and much moreBesides the scientific purpose, this module is well suited for any productionenvironments that need to access the VocalTractLab-backend.VocalTractLab and its Python module are licensed under GPL-3.0.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.