Google Launches Speech Database for 21 African Languages

Imagine asking your phone a question in Yoruba, Luganda, or Hausa and actually getting an answer. Thanks to a new partnership between Google and African universities, that future just got a lot closer.

Google has launched WAXAL, an open-source speech database designed to help developers create voice technology for 21 Sub-Saharan African languages. The project involved institutions across the continent, including Makerere University in Uganda, the University of Ghana, Digital Umuganda in Rwanda, and the African Institute for Mathematical Sciences.

The dataset contains more than 11,000 hours of speech from nearly two million recordings. It covers languages like Hausa, Igbo, Swahili, Yoruba, Fulani, and Acholi, providing the foundation for building speech recognition systems, voice assistants, and text-to-speech tools.

The timing couldn't be better. Sub-Saharan Africa is home to more than 2,000 languages, but fewer than 5% have the resources needed for natural language processing. That means most speech recognition and AI systems simply don't work for African language speakers, leaving more than a billion people out of the digital conversation.

"For AI to have a real impact in Africa, it must speak our languages and understand our contexts," said Joyce Nakatumba-Nabende, Senior Lecturer at Makerere University. "The WAXAL dataset gives our researchers the high-quality data they need to build speech technologies that reflect our unique communities."

Google developed WAXAL over three years with technical support and funding. Under the partnership model, the African institutions that collected the data retain ownership while making it freely available to researchers and developers worldwide.

The Ripple Effect

WAXAL joins a growing movement to bring African languages into the digital age. In September 2025, Nigeria launched N-ATLAS, an open-source language model that recognizes and generates text in Yoruba, Hausa, Igbo, and Nigerian-accented English. South African startup Lelapa AI is building Vulavula, which offers speech recognition, translation, and sentiment analysis for African languages.

These tools have practical applications across education, healthcare, agriculture, and public services. Farmers could get weather updates in their native language. Students could access learning materials without language barriers. Healthcare workers could communicate more effectively with patients.

"This dataset provides the critical foundation for students, researchers, and entrepreneurs to build technology on their own terms, in their own languages," said Aisha Walcott-Bryant, Head of Google Research Africa.

The open-source approach means anyone with the skills and vision can now build voice technology that truly serves African communities, finally giving the continent's languages the digital presence they deserve.