The model, called Sahara v2, supports 24 African languages and recognises more than 500 African English accents. The company said the system was trained using more than 14 million audio clips collected from over 40,000 speakers across Africa and the diaspora.

For many users on the continent, voice technology usually has challenges with everyday phrases and names. Common expressions can be misheard or completely distorted, making digital assistants unreliable for basic tasks.

Developers say the problem lies in how most global systems were built. Many were trained mainly on Western speech patterns and do not align with the tonal nature, accent variety and frequent language mixing common across African countries.

With Sahara v2, Intron says it wants to close that gap by building technology that listens to how people actually speak. The recordings used to train the system were gathered across environments, including clinics, courtrooms, call centres, streets and offices.

The new model covers languages such as Hausa, Swahili, Yoruba, Igbo, Zulu, Twi, Kinyarwanda and Xhosa. In total, Intron says its systems now support 57 languages.

One of the additions is a bilingual speech recognition system that switches between English and Swahili. Intron developed the model with Kenya-based health provider Penda Health to better match how people naturally move between both languages in conversation.

The company also released a Hausa text-to-speech system designed to power local language voice assistants that can run continuously for services such as customer support.

Intron said the new system can also operate offline, allowing organisations to run voice tools locally where privacy or data security is a concern.

According to the company, Sahara v2 performs better on African speech compared with several widely used global models. These include systems developed by Google, OpenAI, Amazon Web Services and Microsoft.

Testing carried out by the company showed stronger accuracy when recognising African names, locations, numbers and sector-specific terms used in areas such as finance, healthcare and telecommunications.

Several organisations have already begun using the system in their services. These include voice banking platforms, medical documentation tools, courtroom transcription systems and automated call centre software.

Ayo Oluleye, head of Data and Insights at ARM Investments, said the model improved the accuracy of automated transcription.

“Using Intron AI models, we’ve seen significant improvement in transcription and summaries compared to models we previously explored. Their systems capture context and nuance better, leading to more accurate results.”

Sarah Morris, chief product officer at Audere, said the system also performed well during testing. “In our testing, accuracy was excellent on several Southern African accents and APIs were robust with 99%+ success rates.”

Alongside the launch, Intron also released its first Africa Voice AI report for 2026, examining how voice technology is being developed and used across the continent.

The report aims to guide governments, businesses, investors and researchers working to expand digital services that rely on speech technology.

Tobi Olatunji, chief executive of Intron, noted that the project shows what happens when technology is designed with local languages in mind.

“Sahara v2 proves that when technology is built with deep cultural and linguistic understanding, amazing things can happen, and we’re just getting started.”

These are required to develop the continent’s own large language models (LLM) to power AI-driven solutions for Africa’s 1.5 billion people, who otherwise risk being sidelined by the global AI ecosystem.

Speaking on ‘The Y’ello Chair Vodcast: Your link to the African continent’, Dr Bosun Tijani, Nigeria’s minister of Communications, Innovation and Digital Economy said that to leapfrog AI in Africa, a collaborative public/private effort was urgently needed to fund the academic research into the continent’s many languages.

He challenged MTN Group, which has operations in 16 markets, 15 of them in Africa, to mobilise resources for this.

“We like these kinds of partnerships. Challenge accepted,” said Ralph Mupita, MTN Group President and CEO in the vodcast, which was filmed on the sidelines of the 80th United Nations General Assembly in New York.

It was hosted by Angela Wamola, who is the head of sub-Saharan Africa for the GSMA mobile industry association.

The vodcast followed the launch of the Nigerian Atlas for Languages & AI at Scale (N-ATLAS). This is an open-source multilingual LLM designed to understand and generate Nigeria’s diverse voices, digitising and preserving the country’s linguistic richness and creating datasets for AI solutions.

More than 500 languages are spoken in Nigeria, the continent’s most populous country.

N-ATLAS is a public/private initiative of the government of Nigeria and Awarri Technologies.

The ATLAS framework is open and available to other African countries, providing a platform for innovation in local languages and in so doing, transform education, health, commerce and governance.

“We have to avoid the risk of Africans being a digital underclass,” Mupita said of the work to ensure that citizens didn’t feel excluded on the continent where there are more than 2 000 languages and most are poorly represented in the global AI ecosystem.

He said the digital economy was the “best bet” to ensure that citizens have dignity, hope and opportunity.

“The outcomes we want are that people are digitally included, economically included and that they have dignity. This dignity point for me is very important because poverty can include all sorts of indignity, but embracing technology should take all that away,” he said.

The Y’ello Chair Vodcast is a platform where leaders and changemakers share insights, challenge norms, and drive Africa’s digital future. For episode 2, see here.

Key Facts

• 16 markets: MTN Group operates in 16 markets, 15 of them in Africa.
• 500+ languages in Nigeria: Nigeria is Africa’s most linguistically diverse country.
• 2,000+ languages in Africa: Most are poorly represented in AI models.
• 1.5 billion people: Africa’s population risks exclusion from the benefits of AI.
• N-ATLAS: Joint initiative between the Nigerian government and Awarri Technologies to digitise and preserve Nigerian languages.