Simba-TTS-xho

Bridging the Digital Divide for African AI

Voice of a Continent is a comprehensive open-source ecosystem designed to bring African languages to the forefront of artificial intelligence. By providing a unified suite of benchmarking tools and state-of-the-art models, we ensure that the future of speech technology is inclusive, representative, and accessible to over a billion people.

Best-in-Class Multilingual Models

Introduced in our EMNLP 2025 paper Voice of a Continent, the Simba Series represents the current state-of-the-art for African speech AI.

• Unified Suite: Models optimized for African languages.
• Superior Accuracy: Outperforms generic multilingual models by leveraging SimbaBench's high-quality, domain-diverse datasets.
• Multitask Capability: Designed for high performance in ASR (Automatic Speech Recognition) and TTS (Text-to-Speech).
• Inclusion-First: Specifically built to mitigate the "digital divide" by empowering speakers of underrepresented languages.

The Simba family consists of state-of-the-art models fine-tuned using SimbaBench. These models achieve superior performance by leveraging dataset quality, domain diversity, and language family relationships.

🔊 Simba-TTS (Text-to-Speech)

• 🎯 Task: Text-to-Speech — Natural Voice Synthesis. 🌍 Language Coverage (7 African languages)

Afrikaans (afr), Asante Twi (asanti), Akuapem Twi (akuapem), Lingala (lin), Southern Sotho (sot), Tswana (tsn), Xhosa (xho)

🧩 Usage Example

You can easily run inference using the Hugging Face transformers library.

from transformers import VitsModel, AutoTokenizer
import torch

model_name="Simba-TTS-afr" ## Simba-TTS-twi-asanti, Simba-TTS-twi-akuapem, Simba-TTS-lin, Simba-TTS-sot, Simba-TTS-tsn, Simba-TTS-xho
model = VitsModel.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

text = "Ons noem hierdie deeltjies sub-atomiese deeltjies" #example of Afrikaans (afr) language 
inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    output = model(**inputs).waveform

The resulting waveform can be saved as a .wav file:

scipy.io.wavfile.write("outputfile.wav", rate=model.config.sampling_rate, data=output.float().numpy())

Citation

If you use the Simba models or SimbaBench benchmark for your scientific publication, or if you find the resources in this website useful, please cite our paper.

@inproceedings{elmadany-etal-2025-voice,
    title = "Voice of a Continent: Mapping {A}frica{'}s Speech Technology Frontier",
    author = "Elmadany, AbdelRahim A.  and
      Kwon, Sang Yun  and
      Toyin, Hawau Olamide  and
      Alcoba Inciarte, Alcides  and
      Aldarmaki, Hanan  and
      Abdul-Mageed, Muhammad",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.559/",
    doi = "10.18653/v1/2025.emnlp-main.559",
    pages = "11039--11061",
    ISBN = "979-8-89176-332-6",
}