Nigerian AI startup Intron has launched Sahara v2, a voice and speech recognition platform designed for Africa’s linguistic diversity. The system aims to deliver more accurate voice AI services for African languages, addressing gaps in global models.
Sahara v2 is built on over 14 million audio samples from 40,000+ speakers across 500 accents, supporting 57 African languages, including Hausa, Swahili, Zulu, Yoruba, Igbo, Xhosa, and African French.
At the virtual launch, CEO Tobi Olatunji said, “Africa doesn’t speak with one voice. It speaks with thousands of accents, dialects, and languages. This is only the beginning.” He added that Sahara v2 tackles limitations in global voice models, especially in recognising code-switching and culturally specific speech.
Read:
Key features include a bilingual Swahili–English speech-recognition model, text-to-speech in languages such as Hausa, voice-activated apps, and offline deployment for low-connectivity environments.
Sarah Morris, Chief Product Officer at Audere, a partner using Sahara for voice transcription, said: “Accuracy was excellent on several Southern African accents, and APIs were robust with 99%+ success rates.”
Already deployed in healthcare, finance, legal, and telecom, Sahara v2 aims to expand digital inclusion and adoption of voice-enabled applications across Africa.
Senior Reporter/Editor
Bio: Ugochukwu is a freelance journalist and Editor at AIbase.ng, with a strong professional focus on investigative reporting. He holds a degree in Mass Communication and brings extensive experience in news gathering, reporting, and editorial writing. With over a decade of active engagement across diverse news outlets, he contributes in-depth analytical, practical, and expository articles exploring artificial intelligence and its real-world impact. His seasoned newsroom experience and well-established information networks provide AIbase.ng with credible, timely, and high-quality coverage of emerging AI developments.