Malian TTS

Voice Synthesis

Generate natural speech in Bambara, Boomu, Dogon, Pular, Songhoy, and Tamasheq using the MALIBA-AI model.

Select Language

Text Input

Synthesizing...

Ready

output.wav

Sampling Rate: 22050 Hz

Malian TTS Models

MALIBA-AI. (2025). Text-to-Speech Models for Six Malian Languages. HuggingFace.

Conditional VAE Architecture

Kim, J., Kong, J., & Son, J. (2021). Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. ICML.

MMS Scaling

Pratap, A. et al. (2023). Scaling Speech Technology to 1,000+ Languages. arXiv.