Intron, a cutting-edge Africa-centric voice technology platform, is accelerating the delivery of justice, patient care, and customer experiences across Africa through Sahara, a suite of best-in-class speech recognition and text-to-speech AI models built specifically for African voices and accents, which outperforms giants like OpenAI, Azure, Google, and AWS at recognising African accents. See publicly available benchmarks and datasets.
Intron initially launched its clinical speech recognition platform in 2022 for hospitals and health ministries throughout Africa. Since then, Intron’s capabilities have expanded, offering advanced real-time voice AI solutions across key sectors, including financial services, telecommunications, legal and government agencies. These solutions are already driving tangible impact and powering voice applications across verticals such as:
- Legal services: Earlier this year, the Ogun State Judiciary adopted Intron Sahara to alleviate the burdens of manual note-taking during court proceedings, allowing judges to focus entirely on the dialogue in the courtroom, enhancing attention, accuracy, and speed. Sahara has significantly reduced session times, enabling more cases to be heard and expediting the delivery of justice.
- Health: Rwanda’s Ministry of Health tapped Intron to accelerate the nationwide rollout of its home-grown electronic medical records, using voice-driven documentation and automated translation to ease adoption for clinicians. At EHA Clinics, a leading hospital with locations in Abuja, Kano, and Lagos, Nigeria, Sahara models cut clinical note times down to 57 seconds for a roughly 100-word report, improving the quality and detail of clinical notes in far less time.
- Call Centres: Digital finance platform, Branch International, is collaborating with Intron to personalise after-hours outbound engagement, improving responsiveness and customer experience using Sahara CX Intelligence–advanced low-latency human-like conversational voice agents.
“Before now, we had to write down everything. It was exhausting and slow. Now, we can focus on what matters. What used to take 4+ hours now concludes in 2–3 hours. My Lord no longer has to write during proceedings. He now focuses entirely on what is being said, ensures everything is properly recorded, and we’re achieving much more in significantly less time than before,” reports the Office of the Chief Registrar, Ogun State High Court.
Over 2 billion people in Africa remain underserved and overlooked by Big Tech, despite AI revolutionising communication, productivity and innovation. As a result, flawed voice recognition systems routinely fail to understand African names, languages and accents. Focusing on speech AI, Sahara tackles these challenges directly with models trained on local data, accurately recognising heavily accented African names, currencies, numbers, decimals and technical terms where imported platforms fall short.
At its core, Sahara is built on a proprietary dataset of more than 3.5 million audio clips from over 18,000 speakers across 30+ countries, powered by Intron’s patented AccentMix algorithm and years of focused R&D. Intron’s speech-to-text models recognise over 300 distinct African accents and dialects, from Ghanaian English to Zulu-inflected speech. Its deep exposure to African speech patterns also enables stronger performance on North African and Arabic-English accents, surpassing expectations beyond its explicit training, outperforming several frontier voice AI models.
Africa-centric AI models powering this new wave of impact include:
- Sahara-Optimus: Inton’s flagship general-purpose cross-domain speech recognition model optimised for African accents
- Sahara-TTS: The first pan-African speech synthesis model supporting 80+ female/male voices, in 40+ African accents spoken across 10+ countries
- Sahara-Voice-Lock: Intelligent Voice authentication [MFA or OTP] and security, tuned for African voices, accents and languages to combat fraud and deepfakes
On the back of this breakthrough and most-recent warchest of over 30,000 hours of local language data in 64+ languages from over 32,000 speakers, Intron is training its next-generation Sahara-Titan model, a single advanced AI model that can understand, transcribe, and translate between 20 of Africa’s top languages like Swahili, Hausa, and Zulu. Similarly, Sahara-Primus will be able to generate fluent, high-quality, and natural-sounding speech in 20 African languages–advanced models that are long overdue and in high demand, ushering in a new era of compelling user experiences across the continent.
Tobi Olatunji, CEO of Intron, says: “Intron represents a future where no community is left behind by technology. Our recent industry-leading benchmarks show what’s possible when Africa builds for itself. Sahara is more than a technical breakthrough; it’s an ecosystem victory. Rather than rail against Big Tech model bias, why not build better models?”
Meaningful AI adoption is on the rise across the continent, and Intron is uniquely positioned to power innovative AI initiatives by startups, enterprises, and government institutions with robust APIs for speech-to-text, text-to-speech, and conversational voicebots tailored for local needs. In South Africa, the digital health nonprofit Audere is integrating Intron’s voice AI into its youth-focused reproductive health chatbot, creating more natural and engaging conversations. C-Care, Uganda’s largest private hospital network, is also leveraging Sahara to cut patient wait times, reduce errors, and ease documentation across its 20+ hospitals and clinics. Intron also collaborates with several enterprises and organisations like Helium Health in Nigeria, the Rural and Urban Private Hospitals Association of Kenya (RUPHA), Rescue.co in Kenya, Aminu Kano Teaching Hospital in Northern Nigeria, and Elephant Healthcare– each driving meaningful and innovative AI applications across Africa.
Olatunji concludes: “Intron was born in the busiest hospital wards, where background noise and scarce resources made accurate speech recognition a daily battle. We built for the hardest environment first, and now our technology scales effortlessly to courts, call centres and content creators. I’m proud of what our team has achieved – but we’re not alone. African AI is rising fast, built by local talent and data. Now is the moment to support, build and buy African so no community is left behind.”
Following a $1.6 million pre-seed raise in 2024, Intron has accelerated R&D, bolstered both cloud-native and on-premises deployments, and continues to grow its Research, Engineering, and Growth teams. Now serving over 40 organisations across 8 countries, the company continues to evolve from its roots in healthcare, becoming the voice-infrastructure layer of choice for startups and enterprises across Africa.
