TWB Voice Text-to-Speech Demo Space

This demo showcases neural Text-to-Speech models developed within the TWB Voice project by CLEAR Global. Currently it supports Hausa and Kanuri languages, developed as part of the first phase of the project.

Features:

  • Hausa: 3 speakers (1 female, 2 male)
  • Kanuri: 1 female speaker
  • High-quality 24kHz audio output
  • Based on YourTTS architecture

Links:
Language

Select the language for synthesis
Speaker

Select the voice speaker

Press to load a sentence in selected language:

Notes:

  • Models work with lowercase input text (automatically converted)
  • Audio output is generated at 24kHz sample rate

License:

This app and the models are released under CC-BY-NC-4.0 license (Non-Commercial use only).

Created by: CLEAR Global with support from the Patrick J. McGovern Foundation